{"meta":{"source":"https://llmpricing.dev","generatedFrom":"models.dev + Artificial Analysis + OpenRouter","syncedAt":"2026-08-21T02:59:41.412Z","models":2537,"providers":193,"providerQuotes":7219,"aaVersion":"4.1","license":"https://creativecommons.org/licenses/by/4.0/","attribution":"Data from models.dev (MIT), Artificial Analysis (https://artificialanalysis.ai/) and OpenRouter. Prices are indicative; confirm on each provider's official page.","docs":"https://llmpricing.dev/en/api/"},"count":2537,"models":[{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[131072,1050000],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"deepseek","input":0.14,"output":0.28,"cacheRead":0.0028,"official":true},"cheapest":{"provider":"unorouter","input":0.0625,"output":0.125,"cacheRead":null},"blendedRef":0.175,"blendedMin":0.0781,"blendedTrusted":0.0929,"spread":7,"hostCount":58,"pricedHostCount":49,"aa":{"idx":42.1,"coding":56.2,"agentic":33.7,"speed":null,"ttft":null,"taskCost":0.0673},"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash/"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","lab":"deepseek","kind":"text","status":"beta","openWeights":true,"context":1000000,"contextRange":[128000,1050000],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"deepseek","input":0.435,"output":0.87,"cacheRead":0.003625,"official":true},"cheapest":{"provider":"routing-run","input":0.348,"output":0.696,"cacheRead":null},"blendedRef":0.5438,"blendedMin":0.435,"blendedTrusted":0.5438,"spread":6.9,"hostCount":60,"pricedHostCount":51,"aa":{"idx":45.3,"coding":59.4,"agentic":37.8,"speed":74,"ttft":1.73,"taskCost":0.0474},"usage":{"rank":7,"tokens":12068587328303,"share":0.045227721992438547},"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro/"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[200000,271360],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"moonshotai","input":0.95,"output":4,"cacheRead":0.19,"official":true},"cheapest":{"provider":"routing-run","input":0.275,"output":1.1,"cacheRead":null},"blendedRef":1.7125,"blendedMin":0.4813,"blendedTrusted":1.36,"spread":4.5,"hostCount":57,"pricedHostCount":50,"aa":{"idx":43,"coding":60.8,"agentic":30.3,"speed":37,"ttft":2.95,"taskCost":0.222},"usage":{"rank":65,"tokens":49583957488,"share":0.00018581871958559128},"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code/"},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"moonshotai","input":0.6,"output":3,"cacheRead":0.1,"official":true},"cheapest":{"provider":"crof","input":0.35,"output":1.7,"cacheRead":0.07},"blendedRef":1.2,"blendedMin":0.6875,"blendedTrusted":0.7875,"spread":2.1,"hostCount":50,"pricedHostCount":43,"aa":{"idx":36,"coding":46.8,"agentic":21.7,"speed":43,"ttft":2.84,"taskCost":0.0964},"usage":{"rank":53,"tokens":334635507639,"share":0.0012540657242294975},"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5/"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","lab":"anthropic","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":[200000,1048576],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":5,"output":25,"cacheRead":0.5,"official":true},"cheapest":{"provider":"poe","input":4.3,"output":21,"cacheRead":0.43},"blendedRef":10,"blendedMin":8.475,"blendedTrusted":9,"spread":7,"hostCount":41,"pricedHostCount":38,"aa":{"idx":55,"coding":73.6,"agentic":46.3,"speed":48,"ttft":15.61,"taskCost":2.2285},"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-7/"},{"id":"openai/gpt-5.5","name":"GPT-5.5","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":1050000,"contextRange":[272000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":5,"output":30,"cacheRead":0.5,"official":true},"cheapest":{"provider":"unorouter","input":0.1875,"output":1.125,"cacheRead":null},"blendedRef":11.25,"blendedMin":0.4219,"blendedTrusted":11.25,"spread":33.3,"hostCount":45,"pricedHostCount":41,"aa":{"idx":56.3,"coding":74.9,"agentic":47.4,"speed":85,"ttft":68.86,"taskCost":1.1747},"usage":{"rank":37,"tokens":906149216771,"share":0.003395846070871285},"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5/"},{"id":"zhipuai/glm-5.2","name":"GLM-5.2","lab":"zhipuai","kind":"text","status":"beta","openWeights":true,"context":1000000,"contextRange":[96000,1049000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"zai","input":1.4,"output":4.4,"cacheRead":0.26,"official":true},"cheapest":{"provider":"crof","input":0.3,"output":1.05,"cacheRead":0.05},"blendedRef":2.15,"blendedMin":0.4875,"blendedTrusted":1.075,"spread":7.7,"hostCount":84,"pricedHostCount":73,"aa":{"idx":52.6,"coding":68.8,"agentic":45.7,"speed":113,"ttft":1.72,"taskCost":0.4445},"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2/"},{"id":"zhipuai/glm-5.1","name":"GLM-5.1","lab":"zhipuai","kind":"text","status":"deprecated","openWeights":true,"context":200000,"contextRange":[163840,204800],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":1.4,"output":4.4,"cacheRead":0.26,"official":true},"cheapest":{"provider":"crof","input":0.45,"output":2.15,"cacheRead":0.08},"blendedRef":2.15,"blendedMin":0.875,"blendedTrusted":1.0763,"spread":3.9,"hostCount":52,"pricedHostCount":46,"aa":{"idx":41,"coding":55.8,"agentic":30.6,"speed":83,"ttft":1.53,"taskCost":0.3042},"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1/"},{"id":"minimax/MiniMax-M2.5","name":"MiniMax-M2.5","lab":"minimax","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":[65536,228700],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"minimax-cn","input":0.3,"output":1.2,"cacheRead":0.03,"official":true},"cheapest":{"provider":"crof","input":0.11,"output":0.95,"cacheRead":0.02},"blendedRef":0.525,"blendedMin":0.32,"blendedTrusted":0.4,"spread":2.7,"hostCount":45,"pricedHostCount":36,"aa":{"idx":34.5,"coding":null,"agentic":null,"speed":94,"ttft":1.66,"taskCost":null},"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/minimax/MiniMax-M2.5/"},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":1050000,"contextRange":[372000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":5,"output":30,"cacheRead":0.5,"official":true},"cheapest":{"provider":"xpersona","input":1.5,"output":12,"cacheRead":0.15},"blendedRef":11.25,"blendedMin":4.125,"blendedTrusted":5.625,"spread":4.2,"hostCount":34,"pricedHostCount":32,"aa":{"idx":60.9,"coding":77.4,"agentic":57.8,"speed":65,"ttft":208.71,"taskCost":1.2312},"usage":{"rank":18,"tokens":3045771685285,"share":0.011414203774409852},"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol/"},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":1050000,"contextRange":[400000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.2,"output":1.2,"cacheRead":0.02,"official":true},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.6,"cacheRead":0.01},"blendedRef":0.45,"blendedMin":0.225,"blendedTrusted":0.45,"spread":10,"hostCount":34,"pricedHostCount":32,"aa":{"idx":52.3,"coding":71.4,"agentic":46.9,"speed":159,"ttft":159.4,"taskCost":0.0471},"usage":{"rank":5,"tokens":17195907845829,"share":0.06444264919348319},"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna/"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":1050000,"contextRange":[372000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":2,"output":12,"cacheRead":0.2,"official":true},"cheapest":{"provider":"xpersona","input":1.5,"output":2,"cacheRead":0.15},"blendedRef":4.5,"blendedMin":1.625,"blendedTrusted":4.5,"spread":3.1,"hostCount":34,"pricedHostCount":32,"aa":{"idx":56.6,"coding":76.7,"agentic":50.2,"speed":119,"ttft":186.73,"taskCost":0.508},"usage":{"rank":20,"tokens":2855988678807,"share":0.010702981091723004},"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra/"},{"id":"openai/gpt-5.4","name":"GPT-5.4","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":1050000,"contextRange":[272000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":2.5,"output":15,"cacheRead":0.25,"official":true},"cheapest":{"provider":"xpersona","input":0.75,"output":6,"cacheRead":0.075},"blendedRef":5.625,"blendedMin":2.0625,"blendedTrusted":5.625,"spread":6.7,"hostCount":42,"pricedHostCount":38,"aa":{"idx":53.1,"coding":71.1,"agentic":44.2,"speed":131,"ttft":144.08,"taskCost":1.1038},"usage":{"rank":38,"tokens":902594624347,"share":0.003382525032246319},"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4/"},{"id":"alibaba/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[131072,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"alibaba","input":0.25,"output":2,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":0.057,"output":0.459,"cacheRead":null},"blendedRef":0.6875,"blendedMin":0.1575,"blendedTrusted":0.355,"spread":5.5,"hostCount":17,"pricedHostCount":17,"aa":{"idx":29.9,"coding":null,"agentic":null,"speed":151,"ttft":2.06,"taskCost":null},"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-35b-a3b/"},{"id":"alibaba/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[131072,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"alibaba-cn","input":0.43,"output":2.58,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":0.172,"output":1.032,"cacheRead":null},"blendedRef":0.9675,"blendedMin":0.387,"blendedTrusted":0.7081,"spread":4.6,"hostCount":29,"pricedHostCount":26,"aa":{"idx":34.3,"coding":48.2,"agentic":19.8,"speed":88,"ttft":2.11,"taskCost":0.3574},"usage":null,"releaseDate":"2026-02-15","lastUpdated":"2026-02-15","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-a17b/"},{"id":"alibaba/qwen3.5-9b","name":"Qwen3.5 9B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[32768,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"pioneer","input":0.3,"output":0.3,"cacheRead":0.3,"official":false},"cheapest":{"provider":"crof","input":0.04,"output":0.15,"cacheRead":0.008},"blendedRef":0.3,"blendedMin":0.0675,"blendedTrusted":0.1125,"spread":7.5,"hostCount":19,"pricedHostCount":18,"aa":{"idx":21.8,"coding":28.7,"agentic":7,"speed":81,"ttft":2.07,"taskCost":0.2416},"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-9b/"},{"id":"alibaba/qwen3.5-27b","name":"Qwen3.5 27B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"alibaba","input":0.3,"output":2.4,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":0.086,"output":0.688,"cacheRead":null},"blendedRef":0.825,"blendedMin":0.2365,"blendedTrusted":0.6875,"spread":3.5,"hostCount":15,"pricedHostCount":15,"aa":{"idx":34.6,"coding":null,"agentic":null,"speed":77,"ttft":5.58,"taskCost":null},"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-27b/"},{"id":"alibaba/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[131072,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"alibaba","input":0.4,"output":3.2,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":0.115,"output":0.917,"cacheRead":null},"blendedRef":1.1,"blendedMin":0.3155,"blendedTrusted":0.715,"spread":4.3,"hostCount":19,"pricedHostCount":18,"aa":{"idx":32.8,"coding":45.7,"agentic":21.3,"speed":130,"ttft":2.33,"taskCost":0.2527},"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-122b-a10b/"},{"id":"alibaba/qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba-cn","input":2.294,"output":6.881,"cacheRead":null,"official":true},"cheapest":{"provider":"cortecs","input":0.25,"output":0.747,"cacheRead":null},"blendedRef":3.4408,"blendedMin":0.3742,"blendedTrusted":0.375,"spread":11.2,"hostCount":9,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/alibaba/qwen2-5-vl-72b-instruct/"},{"id":"alibaba/qwen3-max-preview","name":"Qwen3 Max Preview","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":1.2,"output":6,"cacheRead":0.24,"official":false},"cheapest":{"provider":"vercel","input":1.2,"output":6,"cacheRead":0.24},"blendedRef":2.4,"blendedMin":2.4,"blendedTrusted":2.4,"spread":null,"hostCount":3,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-06","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-max-preview/"},{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","lab":"deepseek","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":[64000,163840],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abacus","input":3,"output":7,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.7,"cacheRead":0.2},"blendedRef":4,"blendedMin":0.725,"blendedTrusted":1.004,"spread":7.5,"hostCount":18,"pricedHostCount":15,"aa":{"idx":18.6,"coding":24.6,"agentic":3.1,"speed":null,"ttft":null,"taskCost":0.3241},"usage":null,"releaseDate":"2025-01-20","lastUpdated":"2025-05-29","url":"https://llmpricing.dev/m/deepseek/deepseek-r1/"},{"id":"misc/kling-v2-6","name":"Kling-V2 6","lab":"misc","kind":"video","status":"ga","openWeights":false,"context":99999999,"contextRange":null,"outputLimit":99999999,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-13","lastUpdated":"2026-01-13","url":"https://llmpricing.dev/m/misc/kling-v2-6/"},{"id":"misc/doubao-1.5-vision-pro","name":"Doubao 1.5 Vision Pro","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/doubao-1.5-vision-pro/"},{"id":"alibaba/qwen-turbo","name":"Qwen Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[128000,1000000],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.044,"output":0.087,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.044,"output":0.087,"cacheRead":null},"blendedRef":0.0548,"blendedMin":0.0548,"blendedTrusted":0.0548,"spread":1.1,"hostCount":5,"pricedHostCount":4,"aa":{"idx":6,"coding":null,"agentic":null,"speed":108,"ttft":2.16,"taskCost":null},"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/alibaba/qwen-turbo/"},{"id":"deepseek/deepseek-v3-0324","name":"DeepSeek V3 0324","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":[75000,163840],"outputLimit":163840,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"crusoe","input":0.5,"output":1.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"submodel","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.35,"blendedTrusted":0.405,"spread":2.5,"hostCount":11,"pricedHostCount":10,"aa":{"idx":15.2,"coding":21.2,"agentic":1.6,"speed":null,"ttft":null,"taskCost":0.0484},"usage":null,"releaseDate":"2025-03-24","lastUpdated":"2025-03-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v3-0324/"},{"id":"alibaba/qwen3-32b","name":"Qwen3 32B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32768,131072],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"alibaba-cn","input":0.287,"output":1.147,"cacheRead":null,"official":true},"cheapest":{"provider":"deepinfra","input":0.08,"output":0.28,"cacheRead":null},"blendedRef":0.502,"blendedMin":0.13,"blendedTrusted":0.13,"spread":11.3,"hostCount":21,"pricedHostCount":19,"aa":{"idx":11.4,"coding":15.3,"agentic":1.8,"speed":101,"ttft":2.46,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-32b/"},{"id":"google/gemini-2.0-flash","name":"Gemini 2.0 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":990000,"contextRange":[990000,1048576],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"poe","input":0.1,"output":0.42,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.1,"output":0.42,"cacheRead":null},"blendedRef":0.18,"blendedMin":0.18,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":{"idx":12.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2024-12-11","url":"https://llmpricing.dev/m/google/gemini-2.0-flash/"},{"id":"misc/qwen-max-2025-01-25","name":"Qwen2.5-Max-2025-01-25","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/qwen-max-2025-01-25/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.4,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"submodel","input":0.2,"output":0.6,"cacheRead":null},"blendedRef":1.3,"blendedMin":0.3,"blendedTrusted":0.975,"spread":2.3,"hostCount":10,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507/"},{"id":"alibaba/qwen3-235b-a22b","name":"Qwen3 235B-A22B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[40960,131072],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"alibaba-cn","input":0.287,"output":1.147,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.5,"cacheRead":0.15},"blendedRef":0.502,"blendedMin":0.35,"blendedTrusted":0.35,"spread":3.5,"hostCount":12,"pricedHostCount":10,"aa":{"idx":13.5,"coding":null,"agentic":null,"speed":61,"ttft":2.73,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b/"},{"id":"alibaba/qwen3-30b-a3b","name":"Qwen3 30B A3B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[40000,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.11,"output":1.08,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.08,"output":0.29,"cacheRead":null},"blendedRef":0.3525,"blendedMin":0.1325,"blendedTrusted":0.215,"spread":1.6,"hostCount":12,"pricedHostCount":11,"aa":{"idx":9.2,"coding":null,"agentic":null,"speed":103,"ttft":2.18,"taskCost":null},"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b/"},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek-V3.1","lab":"deepseek","kind":"text","status":"deprecated","openWeights":true,"context":131072,"contextRange":[75000,164000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"togetherai","input":0.6,"output":1.7,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.7,"cacheRead":0.1},"blendedRef":0.875,"blendedMin":0.325,"blendedTrusted":0.425,"spread":3,"hostCount":19,"pricedHostCount":18,"aa":{"idx":21.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1/"},{"id":"deepseek/deepseek-v3","name":"DeepSeek-V3","lab":"deepseek","kind":"text","status":"deprecated","openWeights":true,"context":131072,"contextRange":[64000,163840],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":1.25,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"deepinfra","input":0.32,"output":0.89,"cacheRead":null},"blendedRef":1.25,"blendedMin":0.4625,"blendedTrusted":0.4625,"spread":4.6,"hostCount":12,"pricedHostCount":9,"aa":{"idx":14.2,"coding":23,"agentic":1.6,"speed":null,"ttft":null,"taskCost":0.0255},"usage":null,"releaseDate":"2024-12-26","lastUpdated":"2024-12-26","url":"https://llmpricing.dev/m/deepseek/deepseek-v3/"},{"id":"misc/gemini-3.0-pro-preview","name":"Gemini 3.0 Pro Preview","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-19","lastUpdated":"2025-11-19","url":"https://llmpricing.dev/m/misc/gemini-3.0-pro-preview/"},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"google-vertex","input":0.1,"output":0.4,"cacheRead":0.01,"official":true},"cheapest":{"provider":"llmtr","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.175,"blendedMin":0.1,"blendedTrusted":0.175,"spread":1.4,"hostCount":21,"pricedHostCount":18,"aa":{"idx":11.4,"coding":null,"agentic":null,"speed":312,"ttft":24.64,"taskCost":null},"usage":{"rank":19,"tokens":2909613455005,"share":0.010903943010778938},"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite/"},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":[75000,164000],"outputLimit":163840,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"huggingface","input":3,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.7,"cacheRead":0.2},"blendedRef":3.5,"blendedMin":0.725,"blendedTrusted":0.9125,"spread":7.5,"hostCount":12,"pricedHostCount":11,"aa":{"idx":20.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-05-28","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-0528/"},{"id":"misc/doubao-seed-1.6-thinking","name":"Doubao-Seed 1.6 Thinking","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["image","text","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-15","lastUpdated":"2025-08-15","url":"https://llmpricing.dev/m/misc/doubao-seed-1.6-thinking/"},{"id":"moonshotai/kimi-k2","name":"Kimi K2","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":256000,"contextRange":[128000,262144],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.57,"output":2.3,"cacheRead":0.5,"official":false},"cheapest":{"provider":"opencode","input":0.4,"output":2.5,"cacheRead":0.4},"blendedRef":1.0025,"blendedMin":0.925,"blendedTrusted":null,"spread":1.4,"hostCount":5,"pricedHostCount":3,"aa":{"idx":19.7,"coding":null,"agentic":null,"speed":41,"ttft":1.22,"taskCost":null},"usage":null,"releaseDate":"2025-07-11","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/moonshotai/kimi-k2/"},{"id":"anthropic/claude-3.7-sonnet","name":"Claude 3.7 Sonnet","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"zenmux","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"merge-gateway","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":1,"hostCount":4,"pricedHostCount":3,"aa":{"idx":27.6,"coding":36.4,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-02-24","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-3.7-sonnet/"},{"id":"misc/claude-4.0-sonnet","name":"Claude 4.0 Sonnet","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/claude-4.0-sonnet/"},{"id":"volcengine/doubao-seed-2.0-mini","name":"Doubao Seed 2.0 Mini","lab":"volcengine","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.0493,"output":0.4845,"cacheRead":0.02465,"official":false},"cheapest":{"provider":"zenmux","input":0.03,"output":0.28,"cacheRead":0.01},"blendedRef":0.1581,"blendedMin":0.0925,"blendedTrusted":null,"spread":1.6,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/volcengine/doubao-seed-2.0-mini/"},{"id":"anthropic/claude-3.5-sonnet","name":"Claude 3.5 Sonnet","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"digitalocean","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":{"idx":9.8,"coding":30.2,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-09","lastUpdated":"2025-09-09","url":"https://llmpricing.dev/m/anthropic/claude-3.5-sonnet/"},{"id":"alibaba/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"clarifai","input":0.3,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.04815,"output":0.19305,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.0844,"blendedTrusted":0.15,"spread":6.2,"hostCount":10,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2025-07-29","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b-instruct-2507/"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[65536,131072],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"regolo-ai","input":1,"output":4.2,"cacheRead":null,"official":false},"cheapest":{"provider":"edenai","input":0.039,"output":0.1,"cacheRead":null},"blendedRef":1.8,"blendedMin":0.0543,"blendedTrusted":0.065,"spread":33.3,"hostCount":69,"pricedHostCount":64,"aa":{"idx":24.1,"coding":30.4,"agentic":13.4,"speed":161,"ttft":0.88,"taskCost":0.0727},"usage":{"rank":25,"tokens":2059132068668,"share":0.007716715321686821},"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b/"},{"id":"misc/gemini-3.0-pro-image-preview","name":"Gemini 3.0 Pro Image Preview","lab":"misc","kind":"image","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-20","lastUpdated":"2025-11-20","url":"https://llmpricing.dev/m/misc/gemini-3.0-pro-image-preview/"},{"id":"misc/claude-4.0-opus","name":"Claude 4.0 Opus","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/claude-4.0-opus/"},{"id":"minimax/minimax-m1","name":"MiniMax M1","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":40000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.55,"output":2.2,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.132,"output":1.254,"cacheRead":null},"blendedRef":0.9625,"blendedMin":0.4125,"blendedTrusted":null,"spread":4.2,"hostCount":6,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/minimax/minimax-m1/"},{"id":"misc/doubao-seed-1.6","name":"Doubao-Seed 1.6","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.204,"output":0.51,"cacheRead":0.102,"official":false},"cheapest":{"provider":"nano-gpt","input":0.204,"output":0.51,"cacheRead":0.102},"blendedRef":0.2805,"blendedMin":0.2805,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-15","lastUpdated":"2025-08-15","url":"https://llmpricing.dev/m/misc/doubao-seed-1.6/"},{"id":"volcengine/doubao-seed-2.0-code","name":"Doubao Seed 2.0 Code","lab":"volcengine","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":0.9,"output":4.48,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.9,"output":4.48,"cacheRead":null},"blendedRef":1.795,"blendedMin":1.795,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-03-20","url":"https://llmpricing.dev/m/volcengine/doubao-seed-2.0-code/"},{"id":"anthropic/claude-4.1-opus","name":"Claude 4.1 Opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":{"idx":34.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-08-06","lastUpdated":"2025-08-06","url":"https://llmpricing.dev/m/anthropic/claude-4.1-opus/"},{"id":"anthropic/claude-4.5-opus","name":"Claude 4.5 Opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-25","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/anthropic/claude-4.5-opus/"},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1065535],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"google-vertex","input":0.3,"output":2.5,"cacheRead":0.03,"official":true},"cheapest":{"provider":"qihang-ai","input":0.09,"output":0.71,"cacheRead":null},"blendedRef":0.85,"blendedMin":0.245,"blendedTrusted":0.85,"spread":3.3,"hostCount":31,"pricedHostCount":28,"aa":{"idx":20.3,"coding":null,"agentic":null,"speed":225,"ttft":19.09,"taskCost":null},"usage":{"rank":23,"tokens":2266164553573,"share":0.008492581412387241},"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash/"},{"id":"alibaba/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[65536,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":1.434,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.65,"cacheRead":0.075},"blendedRef":0.4665,"blendedMin":0.275,"blendedTrusted":0.4125,"spread":3.5,"hostCount":16,"pricedHostCount":15,"aa":null,"usage":null,"releaseDate":"2025-09","lastUpdated":"2025-09","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-thinking/"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[106000,262144],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.861,"output":3.441,"cacheRead":null,"official":true},"cheapest":{"provider":"submodel","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":1.506,"blendedMin":0.35,"blendedTrusted":0.615,"spread":10,"hostCount":17,"pricedHostCount":15,"aa":{"idx":18.2,"coding":null,"agentic":null,"speed":66,"ttft":3.16,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-480b-a35b-instruct/"},{"id":"misc/doubao-1.5-pro-32k","name":"Doubao 1.5 Pro 32k","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":[32000,128000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1343,"output":0.3349,"cacheRead":0.06715,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1343,"output":0.3349,"cacheRead":0.06715},"blendedRef":0.1845,"blendedMin":0.1845,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/doubao-1.5-pro-32k/"},{"id":"alibaba/qwen3-max","name":"Qwen3 Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[131072,262144],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.861,"output":3.441,"cacheRead":null,"official":true},"cheapest":{"provider":"ofox","input":0.36,"output":1.43,"cacheRead":0.072},"blendedRef":1.506,"blendedMin":0.6275,"blendedTrusted":1.506,"spread":5.9,"hostCount":20,"pricedHostCount":16,"aa":{"idx":24.5,"coding":null,"agentic":null,"speed":58,"ttft":2.44,"taskCost":null},"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-max/"},{"id":"volcengine/doubao-seed-2.0-lite","name":"Doubao Seed 2.0 Lite","lab":"volcengine","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.1462,"output":0.8738,"cacheRead":0.0731,"official":false},"cheapest":{"provider":"zenmux","input":0.09,"output":0.51,"cacheRead":0.02},"blendedRef":0.3281,"blendedMin":0.195,"blendedTrusted":null,"spread":1.6,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/volcengine/doubao-seed-2.0-lite/"},{"id":"misc/doubao-1.5-thinking-pro","name":"Doubao 1.5 Thinking Pro","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/doubao-1.5-thinking-pro/"},{"id":"misc/claude-4.5-haiku","name":"Claude 4.5 Haiku","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":29.9,"coding":43.9,"agentic":16.5,"speed":89,"ttft":16.69,"taskCost":0.2174},"usage":{"rank":34,"tokens":1029904298053,"share":0.0038596253234974465},"releaseDate":"2025-10-16","lastUpdated":"2025-10-16","url":"https://llmpricing.dev/m/misc/claude-4.5-haiku/"},{"id":"alibaba/qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL 7B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba-cn","input":0.287,"output":0.717,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.287,"output":0.717,"cacheRead":null},"blendedRef":0.3945,"blendedMin":0.3945,"blendedTrusted":0.3945,"spread":1.2,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/alibaba/qwen2-5-vl-7b-instruct/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.026,"output":3.078,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.069,"output":0.455,"cacheRead":0.018},"blendedRef":1.539,"blendedMin":0.1655,"blendedTrusted":0.205,"spread":17.4,"hostCount":20,"pricedHostCount":18,"aa":{"idx":18.4,"coding":null,"agentic":null,"speed":56,"ttft":2.39,"taskCost":null},"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-07-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507/"},{"id":"alibaba/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[65536,262144],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.574,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.144,"output":0.574,"cacheRead":null},"blendedRef":0.2515,"blendedMin":0.2515,"blendedTrusted":0.2515,"spread":5.6,"hostCount":19,"pricedHostCount":17,"aa":{"idx":13.8,"coding":null,"agentic":null,"speed":183,"ttft":2.19,"taskCost":null},"usage":null,"releaseDate":"2025-09","lastUpdated":"2025-09","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-instruct/"},{"id":"google/gemini-2.0-flash-lite","name":"Gemini 2.0 Flash-Lite","lab":"google","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":[990000,2000000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"302ai","input":0.075,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.052,"output":0.21,"cacheRead":null},"blendedRef":0.1312,"blendedMin":0.0915,"blendedTrusted":null,"spread":1.4,"hostCount":3,"pricedHostCount":2,"aa":{"idx":8.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2024-12-11","url":"https://llmpricing.dev/m/google/gemini-2.0-flash-lite/"},{"id":"alibaba/qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":81920,"contextRange":[81920,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.2,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"clarifai","input":0.36,"output":1.3,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.595,"blendedTrusted":0.595,"spread":1.8,"hostCount":4,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-04","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b-thinking-2507/"},{"id":"xiaomi/mimo-v2-flash","name":"MiMo-V2-Flash","lab":"xiaomi","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi","input":0.14,"output":0.28,"cacheRead":0.0028,"official":true},"cheapest":{"provider":"qiniu-ai","input":0.1,"output":0.3,"cacheRead":0.01},"blendedRef":0.175,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1.4,"hostCount":5,"pricedHostCount":5,"aa":{"idx":34,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-flash/"},{"id":"misc/doubao-seed-1.6-flash","name":"Doubao-Seed 1.6 Flash","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.0374,"output":0.374,"cacheRead":0.0187,"official":false},"cheapest":{"provider":"nano-gpt","input":0.0374,"output":0.374,"cacheRead":0.0187},"blendedRef":0.1216,"blendedMin":0.1216,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-15","lastUpdated":"2025-08-15","url":"https://llmpricing.dev/m/misc/doubao-seed-1.6-flash/"},{"id":"zhipuai/glm-4.5-air","name":"GLM-4.5-Air","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":0.2,"output":1.1,"cacheRead":0.03,"official":true},"cheapest":{"provider":"302ai","input":0.1143,"output":0.286,"cacheRead":null},"blendedRef":0.425,"blendedMin":0.1572,"blendedTrusted":0.31,"spread":2,"hostCount":16,"pricedHostCount":15,"aa":{"idx":16.7,"coding":null,"agentic":null,"speed":77,"ttft":2.63,"taskCost":null},"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-air/"},{"id":"alibaba/qwen3-vl-30b-a3b-thinking","name":"Qwen3-Vl 30b A3b Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[128000,262144],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"openrouter","input":0.2,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.2,"output":2.4,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-09","lastUpdated":"2026-02-09","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-30b-a3b-thinking/"},{"id":"misc/qwen-vl-max-2025-01-25","name":"Qwen VL-MAX-2025-01-25","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/misc/qwen-vl-max-2025-01-25/"},{"id":"anthropic/claude-3.5-haiku","name":"Claude 3.5 Haiku","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"zenmux","input":0.8,"output":4,"cacheRead":0.08,"official":false},"cheapest":{"provider":"digitalocean","input":0.8,"output":4,"cacheRead":0.08},"blendedRef":1.6,"blendedMin":1.6,"blendedTrusted":1.6,"spread":1,"hostCount":3,"pricedHostCount":2,"aa":{"idx":12.2,"coding":15.9,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/anthropic/claude-3.5-haiku/"},{"id":"google/gemini-2.5-flash-image","name":"Gemini 2.5 Flash Image","lab":"google","kind":"image","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.3,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":0.3,"output":2.5,"cacheRead":null},"blendedRef":7.725,"blendedMin":0.85,"blendedTrusted":null,"spread":1,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-22","lastUpdated":"2025-10-22","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-image/"},{"id":"volcengine/doubao-seed-2.0-pro","name":"Doubao Seed 2.0 Pro","lab":"volcengine","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.782,"output":3.876,"cacheRead":0.391,"official":false},"cheapest":{"provider":"zenmux","input":0.45,"output":2.24,"cacheRead":0.09},"blendedRef":1.5555,"blendedMin":0.8975,"blendedTrusted":null,"spread":1.7,"hostCount":4,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/volcengine/doubao-seed-2.0-pro/"},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1065535],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":1.25,"output":10,"cacheRead":0.125,"official":true},"cheapest":{"provider":"poe","input":0.87,"output":7,"cacheRead":0.087},"blendedRef":3.4375,"blendedMin":2.4025,"blendedTrusted":3.4375,"spread":2.9,"hostCount":29,"pricedHostCount":27,"aa":{"idx":25.9,"coding":33.3,"agentic":7.2,"speed":133,"ttft":20.46,"taskCost":0.2164},"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-pro/"},{"id":"misc/claude-4.5-sonnet","name":"Claude 4.5 Sonnet","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":37.4,"coding":52.1,"agentic":26.4,"speed":40,"ttft":12.43,"taskCost":0.4643},"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/misc/claude-4.5-sonnet/"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","lab":"openai","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":[64000,131072],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"regolo-ai","input":0.4,"output":1.8,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.03,"output":0.13,"cacheRead":0.03},"blendedRef":0.75,"blendedMin":0.055,"blendedTrusted":0.055,"spread":13.3,"hostCount":45,"pricedHostCount":39,"aa":{"idx":15.2,"coding":20.7,"agentic":3.1,"speed":136,"ttft":0.98,"taskCost":0.025},"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-20b/"},{"id":"misc/gemini-3.0-flash-preview","name":"Gemini 3.0 Flash Preview","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/misc/gemini-3.0-flash-preview/"},{"id":"zhipuai/glm-4.5","name":"GLM-4.5","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":0.6,"output":2.2,"cacheRead":0.11,"official":true},"cheapest":{"provider":"302ai","input":0.286,"output":1.142,"cacheRead":null},"blendedRef":1,"blendedMin":0.5,"blendedTrusted":1,"spread":2.1,"hostCount":18,"pricedHostCount":16,"aa":{"idx":19.7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5/"},{"id":"zhipuai/glm-4.6","name":"Z-AI/GLM 4.6","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":204800,"contextRange":[200000,204800],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.44999999999999996,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.44999999999999996,"output":1.5,"cacheRead":null},"blendedRef":0.7125,"blendedMin":0.7125,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-11","lastUpdated":"2025-10-11","url":"https://llmpricing.dev/m/zhipuai/glm-4.6/"},{"id":"zhipuai/glm-4.7","name":"Z-Ai/GLM 4.7","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":200000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/zhipuai/glm-4.7/"},{"id":"zhipuai/glm-5","name":"Z-Ai/GLM 5","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5/"},{"id":"zhipuai/autoglm-phone-9b","name":"Z-Ai/Autoglm Phone 9b","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":12800,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/zhipuai/autoglm-phone-9b/"},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek/DeepSeek-V3.1-Terminus","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[128000,131072],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.27,"output":1,"cacheRead":0.135,"official":false},"cheapest":{"provider":"kilo","input":0.27,"output":1,"cacheRead":0.135},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-22","lastUpdated":"2025-09-22","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus/"},{"id":"deepseek/deepseek-v3.2-exp-thinking","name":"DeepSeek/DeepSeek-V3.2-Exp-Thinking","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-exp-thinking/"},{"id":"deepseek/deepseek-v3.2-251201","name":"Deepseek/DeepSeek-V3.2","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-251201/"},{"id":"deepseek/deepseek-math-v2","name":"Deepseek/Deepseek-Math-V2","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":160000,"contextRange":null,"outputLimit":160000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-04","lastUpdated":"2025-12-04","url":"https://llmpricing.dev/m/deepseek/deepseek-math-v2/"},{"id":"deepseek/deepseek-v3.1-terminus-thinking","name":"DeepSeek/DeepSeek-V3.1-Terminus-Thinking","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-22","lastUpdated":"2025-09-22","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus-thinking/"},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek/DeepSeek-V3.2-Exp","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":[128000,163840],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.27,"output":0.41,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.27,"output":0.41,"cacheRead":null},"blendedRef":0.305,"blendedMin":0.305,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-exp/"},{"id":"xai/grok-4-fast-reasoning","name":"X-Ai/Grok-4-Fast-Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996,"official":false},"cheapest":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/xai/grok-4-fast-reasoning/"},{"id":"xai/grok-4.1-fast-reasoning","name":"X-Ai/Grok 4.1 Fast Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":[2000000,20000000],"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996,"official":false},"cheapest":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-19","lastUpdated":"2025-12-19","url":"https://llmpricing.dev/m/xai/grok-4.1-fast-reasoning/"},{"id":"xai/grok-code-fast-1","name":"x-AI/Grok-Code-Fast 1","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":10000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.19999999999999998,"output":1.5,"cacheRead":0.02,"official":false},"cheapest":{"provider":"helicone","input":0.19999999999999998,"output":1.5,"cacheRead":0.02},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-02","lastUpdated":"2025-09-02","url":"https://llmpricing.dev/m/xai/grok-code-fast-1/"},{"id":"xai/grok-4-fast","name":"x-AI/Grok-4-Fast","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-20","lastUpdated":"2025-09-20","url":"https://llmpricing.dev/m/xai/grok-4-fast/"},{"id":"xai/grok-4.1-fast","name":"x-AI/Grok-4.1-Fast","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-20","lastUpdated":"2025-11-20","url":"https://llmpricing.dev/m/xai/grok-4.1-fast/"},{"id":"xai/grok-4.1-fast-non-reasoning","name":"X-Ai/Grok 4.1 Fast Non Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996,"official":false},"cheapest":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-19","lastUpdated":"2025-12-19","url":"https://llmpricing.dev/m/xai/grok-4.1-fast-non-reasoning/"},{"id":"xai/grok-4-fast-non-reasoning","name":"X-Ai/Grok-4-Fast-Non-Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996,"official":false},"cheapest":{"provider":"helicone","input":0.19999999999999998,"output":0.5,"cacheRead":0.049999999999999996},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/xai/grok-4-fast-non-reasoning/"},{"id":"moonshotai/kimi-k2.5-2","name":"Moonshotai/Kimi-K2.5","lab":"moonshotai","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":[256000,262000],"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow","input":0.45,"output":2.25,"cacheRead":0.07,"official":false},"cheapest":{"provider":"siliconflow","input":0.45,"output":2.25,"cacheRead":0.07},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":0.9,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-28","lastUpdated":"2026-01-28","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-2/"},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"moonshotai","input":0.6,"output":2.5,"cacheRead":0.15,"official":true},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2},"blendedRef":1.075,"blendedMin":0.75,"blendedTrusted":1.075,"spread":1.5,"hostCount":11,"pricedHostCount":8,"aa":{"idx":24,"coding":null,"agentic":null,"speed":41,"ttft":1.13,"taskCost":null},"usage":null,"releaseDate":"2025-09-05","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-0905/"},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"moonshotai","input":0.6,"output":2.5,"cacheRead":0.15,"official":true},"cheapest":{"provider":"vercel","input":0.47,"output":2,"cacheRead":0.141},"blendedRef":1.075,"blendedMin":0.8525,"blendedTrusted":0.8525,"spread":1.5,"hostCount":21,"pricedHostCount":19,"aa":{"idx":33.5,"coding":null,"agentic":null,"speed":121,"ttft":1.24,"taskCost":null},"usage":null,"releaseDate":"2025-11-06","lastUpdated":"2025-11-06","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-thinking/"},{"id":"openai/gpt-5","name":"OpenAI GPT-5","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003,"official":false},"cheapest":{"provider":"digitalocean","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":3.4375,"spread":1,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-19","lastUpdated":"2025-09-19","url":"https://llmpricing.dev/m/openai/gpt-5/"},{"id":"openai/gpt-5.2","name":"OpenAI/GPT-5.2","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"digitalocean","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":4.8125,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":{"rank":63,"tokens":53382733795,"share":0.00020005485129269947},"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2/"},{"id":"stepfun/gelab-zero-4b-preview","name":"Stepfun-Ai/Gelab Zero 4b Preview","lab":"stepfun","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/stepfun/gelab-zero-4b-preview/"},{"id":"meituan/longcat-flash-chat","name":"Meituan/Longcat-Flash-Chat","lab":"meituan","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-05","lastUpdated":"2025-11-05","url":"https://llmpricing.dev/m/meituan/longcat-flash-chat/"},{"id":"meituan/longcat-flash-lite","name":"Meituan/Longcat-Flash-Lite","lab":"meituan","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":320000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":17.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-02-06","lastUpdated":"2026-02-06","url":"https://llmpricing.dev/m/meituan/longcat-flash-lite/"},{"id":"stepfun/step-3.5-flash","name":"Stepfun/Step-3.5 Flash","lab":"stepfun","kind":"text","status":"ga","openWeights":false,"context":64000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-02","lastUpdated":"2026-02-02","url":"https://llmpricing.dev/m/stepfun/step-3.5-flash/"},{"id":"xiaomi/mimo-v2-flash-2","name":"Xiaomi/Mimo-V2-Flash","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"qiniu-ai","input":0.1,"output":0.3,"cacheRead":0.01,"official":false},"cheapest":{"provider":"qiniu-ai","input":0.1,"output":0.3,"cacheRead":0.01},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-flash-2/"},{"id":"minimax/minimax-m2.5-highspeed","name":"Minimax/Minimax-M2.5 Highspeed","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":204800,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-highspeed/"},{"id":"minimax/minimax-m2","name":"Minimax/Minimax-M2","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-28","lastUpdated":"2025-10-28","url":"https://llmpricing.dev/m/minimax/minimax-m2/"},{"id":"minimax/minimax-m2.5","name":"Minimax/Minimax-M2.5","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":204800,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/minimax/minimax-m2.5/"},{"id":"minimax/minimax-m2.1","name":"Minimax/Minimax-M2.1","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":204800,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/minimax-m2.1/"},{"id":"alibaba/qwen3.6-35b-fast","name":"Qwen3.6 35B Fast","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131056,"contextRange":null,"outputLimit":131056,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"neuralwatt","input":0.29,"output":1.15,"cacheRead":0.0725,"official":false},"cheapest":{"provider":"neuralwatt","input":0.29,"output":1.15,"cacheRead":0.0725},"blendedRef":0.505,"blendedMin":0.505,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-04-01","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-fast/"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","lab":"moonshotai","kind":"text","status":"beta","openWeights":true,"context":1048576,"contextRange":[262144,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"moonshotai","input":3,"output":15,"cacheRead":0.3,"official":true},"cheapest":{"provider":"crof","input":2,"output":8,"cacheRead":0.25},"blendedRef":6,"blendedMin":3.5,"blendedTrusted":5.7,"spread":2.3,"hostCount":56,"pricedHostCount":51,"aa":{"idx":59.7,"coding":76.2,"agentic":54.3,"speed":38,"ttft":2.67,"taskCost":0.8375},"usage":{"rank":12,"tokens":5837932722057,"share":0.02187798712319389},"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3/"},{"id":"moonshotai/kimi-k3-fast","name":"Kimi K3 Fast","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"fireworks-ai","input":4.5,"output":22.5,"cacheRead":0.45,"official":false},"cheapest":{"provider":"neuralwatt","input":3,"output":15,"cacheRead":0.3},"blendedRef":9,"blendedMin":6,"blendedTrusted":9,"spread":1.5,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-fast/"},{"id":"zhipuai/glm-5.2-fast","name":"GLM 5.2 Fast","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"wafer.ai","input":3,"output":10.25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"neuralwatt","input":1.45,"output":4.5,"cacheRead":0.3625},"blendedRef":4.8125,"blendedMin":2.2125,"blendedTrusted":3.225,"spread":2.1,"hostCount":6,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-07-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-fast/"},{"id":"zhipuai/glm-5.2-flex","name":"GLM 5.2 Flex","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048560,"contextRange":null,"outputLimit":1048560,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neuralwatt","input":0.725,"output":2.25,"cacheRead":0.18125,"official":false},"cheapest":{"provider":"neuralwatt","input":0.725,"output":2.25,"cacheRead":0.18125},"blendedRef":1.1063,"blendedMin":1.1063,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-flex/"},{"id":"zhipuai/glm-5.2-short","name":"GLM 5.2 Short","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":199984,"contextRange":null,"outputLimit":199984,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neuralwatt","input":1.45,"output":4.5,"cacheRead":0.3625,"official":false},"cheapest":{"provider":"neuralwatt","input":1.45,"output":4.5,"cacheRead":0.3625},"blendedRef":2.2125,"blendedMin":2.2125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-short/"},{"id":"google/gemma-4-31b","name":"Gemma 4 31B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[262128,262144],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.4,"output":1,"cacheRead":0.4,"official":false},"cheapest":{"provider":"wandb","input":0.1,"output":0.34,"cacheRead":0.1},"blendedRef":0.55,"blendedMin":0.16,"blendedTrusted":0.16,"spread":4,"hostCount":7,"pricedHostCount":5,"aa":{"idx":29.7,"coding":43.4,"agentic":14.4,"speed":36,"ttft":1.11,"taskCost":0},"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-08","url":"https://llmpricing.dev/m/google/gemma-4-31b/"},{"id":"moonshotai/kimi-k2.5-fast","name":"Kimi K2.5 Fast","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262128,"contextRange":[256000,262128],"outputLimit":262128,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"neuralwatt","input":0.52,"output":2.59,"cacheRead":0.13,"official":false},"cheapest":{"provider":"nebius","input":0.5,"output":2.5,"cacheRead":0.05},"blendedRef":1.0375,"blendedMin":1,"blendedTrusted":1,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-fast/"},{"id":"moonshotai/kimi-k2.6-flex","name":"Kimi K2.6 Flex","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262128,"contextRange":null,"outputLimit":262128,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"neuralwatt","input":0.345,"output":1.61,"cacheRead":0.08625,"official":false},"cheapest":{"provider":"neuralwatt","input":0.345,"output":1.61,"cacheRead":0.08625},"blendedRef":0.6613,"blendedMin":0.6613,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-flex/"},{"id":"alibaba/qwen3.5-397b-fast","name":"Qwen3.5 397B Fast","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262128,"contextRange":null,"outputLimit":262128,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neuralwatt","input":0.69,"output":4.14,"cacheRead":0.1725,"official":false},"cheapest":{"provider":"neuralwatt","input":0.69,"output":4.14,"cacheRead":0.1725},"blendedRef":1.5525,"blendedMin":1.5525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-02-01","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-fast/"},{"id":"zhipuai/glm-5.2-short-fast-flex","name":"GLM 5.2 Short Fast Flex","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":199984,"contextRange":null,"outputLimit":199984,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neuralwatt","input":0.725,"output":2.25,"cacheRead":0.18125,"official":false},"cheapest":{"provider":"neuralwatt","input":0.725,"output":2.25,"cacheRead":0.18125},"blendedRef":1.1063,"blendedMin":1.1063,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-short-fast-flex/"},{"id":"moonshotai/kimi-k2.6-fast","name":"Kimi K2.6 Fast","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262000,"contextRange":[262000,262144],"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"fireworks-ai","input":2,"output":8,"cacheRead":0.3,"official":false},"cheapest":{"provider":"neuralwatt","input":0.69,"output":3.22,"cacheRead":0.1725},"blendedRef":3.5,"blendedMin":1.3225,"blendedTrusted":3.5,"spread":2.9,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-06-05","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-fast/"},{"id":"zhipuai/glm-5.2-short-fast","name":"GLM 5.2 Short Fast","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":199984,"contextRange":null,"outputLimit":199984,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neuralwatt","input":1.45,"output":4.5,"cacheRead":0.3625,"official":false},"cheapest":{"provider":"neuralwatt","input":1.45,"output":4.5,"cacheRead":0.3625},"blendedRef":2.2125,"blendedMin":2.2125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-short-fast/"},{"id":"moonshotai/kimi-k2.7-code-flex","name":"Kimi K2.7 Code Flex","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"neuralwatt","input":0.475,"output":2,"cacheRead":0.11875,"official":false},"cheapest":{"provider":"neuralwatt","input":0.475,"output":2,"cacheRead":0.11875},"blendedRef":0.8563,"blendedMin":0.8563,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-flex/"},{"id":"zhipuai/glm-5.2-short-flex","name":"GLM 5.2 Short Flex","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":199984,"contextRange":null,"outputLimit":199984,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neuralwatt","input":0.725,"output":2.25,"cacheRead":0.18125,"official":false},"cheapest":{"provider":"neuralwatt","input":0.725,"output":2.25,"cacheRead":0.18125},"blendedRef":1.1063,"blendedMin":1.1063,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-short-flex/"},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","lab":"moonshotai","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[65536,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"moonshotai","input":0.95,"output":4,"cacheRead":0.16,"official":true},"cheapest":{"provider":"llmgateway","input":0.22,"output":1.137,"cacheRead":0.048},"blendedRef":1.7125,"blendedMin":0.4493,"blendedTrusted":0.525,"spread":8.1,"hostCount":65,"pricedHostCount":59,"aa":{"idx":45.1,"coding":61.8,"agentic":31.2,"speed":46,"ttft":2.74,"taskCost":0.3653},"usage":{"rank":48,"tokens":534423517525,"share":0.002002782730018206},"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6/"},{"id":"alibaba/qwen3.5-397b-a17b-fp8","name":"Qwen3.5 397B A17B FP8","lab":"alibaba","kind":"text","status":"beta","openWeights":true,"context":200000,"contextRange":[200000,262128],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"infomaniak","input":0.99,"output":4.46,"cacheRead":null,"official":false},"cheapest":{"provider":"neuralwatt","input":0.69,"output":4.14,"cacheRead":0.1725},"blendedRef":1.8575,"blendedMin":1.5525,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-a17b-fp8/"},{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","lab":"alibaba","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[16384,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"alibaba","input":0.248,"output":1.485,"cacheRead":null,"official":true},"cheapest":{"provider":"empiriolabs","input":0.07,"output":0.42,"cacheRead":0.035},"blendedRef":0.5573,"blendedMin":0.1575,"blendedTrusted":0.3125,"spread":71.4,"hostCount":25,"pricedHostCount":23,"aa":{"idx":32.1,"coding":41.9,"agentic":21.6,"speed":118,"ttft":2.07,"taskCost":0.2944},"usage":{"rank":61,"tokens":137445127935,"share":0.0005150834862735692},"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b/"},{"id":"moonshotai/umans-coder","name":"Umans Coder","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"umans-ai","input":0.95,"output":4,"cacheRead":0.19,"official":false},"cheapest":{"provider":"umans-ai","input":0.95,"output":4,"cacheRead":0.19},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/umans-coder/"},{"id":"alibaba/umans-flash","name":"Umans Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"umans-ai","input":0.15,"output":1,"cacheRead":0.05,"official":false},"cheapest":{"provider":"umans-ai","input":0.15,"output":1,"cacheRead":0.05},"blendedRef":0.3625,"blendedMin":0.3625,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/umans-flash/"},{"id":"nvidia/nemotron-3-120b-a12b","name":"Nemotron 3 Super 120B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[256000,1000000],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"perplexity-agent","input":0.25,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.3,"output":0.9,"cacheRead":null},"blendedRef":0.8125,"blendedMin":0.45,"blendedTrusted":0.75,"spread":2,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-120b-a12b/"},{"id":"aisingapore/gemma-sea-lion-v4-27b-it","name":"Gemma-SEA-LION-v4-27B-IT","lab":"aisingapore","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"edenai","input":0.351,"output":0.555,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudflare-workers-ai","input":0.351,"output":0.555,"cacheRead":null},"blendedRef":0.402,"blendedMin":0.402,"blendedTrusted":0.402,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/aisingapore/gemma-sea-lion-v4-27b-it/"},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","lab":"google","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":null,"cheapest":{"provider":"kilo","input":0.05,"output":0.25,"cacheRead":null},"blendedRef":null,"blendedMin":0.1,"blendedTrusted":0.1375,"spread":5,"hostCount":17,"pricedHostCount":16,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-it/"},{"id":"meta/llama-3.1-8b-instruct-fp8","name":"Llama 3.1 8B Instruct fp8","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudflare-ai-gateway","input":0.152,"output":0.287,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudflare-workers-ai","input":0.152,"output":0.287,"cacheRead":null},"blendedRef":0.1857,"blendedMin":0.1857,"blendedTrusted":0.1857,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-8b-instruct-fp8/"},{"id":"meta/llama-3.3-70b-instruct-fp8-fast","name":"Llama 3.3 70B Instruct fp8 Fast","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":24000,"contextRange":null,"outputLimit":24000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudflare-ai-gateway","input":0.293,"output":2.253,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudflare-workers-ai","input":0.293,"output":2.253,"cacheRead":null},"blendedRef":0.783,"blendedMin":0.783,"blendedTrusted":0.783,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct-fp8-fast/"},{"id":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[16000,131072],"outputLimit":80000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"pioneer","input":0.1,"output":0.335,"cacheRead":0.1,"official":false},"cheapest":{"provider":"inference","input":0.02,"output":0.02,"cacheRead":null},"blendedRef":0.1588,"blendedMin":0.02,"blendedTrusted":0.1219,"spread":5,"hostCount":9,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/meta/llama-3.2-3b-instruct/"},{"id":"meta/llama-guard-3-8b","name":"Llama-Guard-3-8B","lab":"meta","kind":"classify","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"edenai","input":0.484,"output":0.03,"cacheRead":null,"official":false},"cheapest":{"provider":"edenai","input":0.055,"output":0.055,"cacheRead":null},"blendedRef":0.3705,"blendedMin":0.055,"blendedTrusted":0.3705,"spread":8.8,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-guard-3-8b/"},{"id":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[16000,131072],"outputLimit":60000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.1,"output":0.201,"cacheRead":0.1,"official":false},"cheapest":{"provider":"inference","input":0.01,"output":0.01,"cacheRead":null},"blendedRef":0.1253,"blendedMin":0.01,"blendedTrusted":0.0705,"spread":10,"hostCount":6,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/meta/llama-3.2-1b-instruct/"},{"id":"meta/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":[128000,131000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cloudflare-ai-gateway","input":0.27,"output":0.85,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.2,"output":0.78,"cacheRead":null},"blendedRef":0.415,"blendedMin":0.345,"blendedTrusted":0.345,"spread":1.4,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-16e-instruct/"},{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama-3.2-11B-Vision-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[16000,131072],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"edenai","input":0.345,"output":0.345,"cacheRead":null,"official":false},"cheapest":{"provider":"inference","input":0.055,"output":0.055,"cacheRead":null},"blendedRef":0.345,"blendedMin":0.055,"blendedTrusted":0.2054,"spread":7.1,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-11b-vision-instruct/"},{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek-R1-Distill-Qwen-32B","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":80000,"contextRange":[32768,80000],"outputLimit":80000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudflare-ai-gateway","input":0.497,"output":4.881,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.3,"output":0.3,"cacheRead":null},"blendedRef":1.593,"blendedMin":0.3,"blendedTrusted":0.4305,"spread":1.7,"hostCount":4,"pricedHostCount":4,"aa":{"idx":11,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-20","lastUpdated":"2025-01-20","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-distill-qwen-32b/"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","lab":"deepseek","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":[1000000,1048576],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":1.65,"output":4.95,"cacheRead":0.165,"official":false},"cheapest":{"provider":"runinfra","input":0.6,"output":1.9,"cacheRead":0.03},"blendedRef":2.475,"blendedMin":0.925,"blendedTrusted":1.625,"spread":2.8,"hostCount":26,"pricedHostCount":24,"aa":{"idx":53.2,"coding":68.8,"agentic":49.6,"speed":74,"ttft":1.66,"taskCost":0.2521},"usage":{"rank":32,"tokens":1224592288788,"share":0.00458922971551929},"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-0813/"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[256000,1310720],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"hyper","input":0.479072,"output":1.437216,"cacheRead":0.015243,"official":false},"cheapest":{"provider":"deepinfra","input":0.08,"output":0.18,"cacheRead":0.016},"blendedRef":0.7186,"blendedMin":0.105,"blendedTrusted":0.105,"spread":6,"hostCount":40,"pricedHostCount":36,"aa":{"idx":51.8,"coding":69.1,"agentic":48.4,"speed":103,"ttft":1.23,"taskCost":0.1122},"usage":{"rank":3,"tokens":28266255596243,"share":0.10592941121418317},"releaseDate":"2026-07-31","lastUpdated":"2026-07-31","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-0731/"},{"id":"alibaba/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3b fp8","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudflare-ai-gateway","input":0.0509,"output":0.335,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudflare-workers-ai","input":0.0509,"output":0.335,"cacheRead":null},"blendedRef":0.1219,"blendedMin":0.1219,"blendedTrusted":0.1219,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b-fp8/"},{"id":"alibaba/qwq-32b","name":"QwQ 32B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[24000,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.287,"output":0.861,"cacheRead":null,"official":true},"cheapest":{"provider":"abacus","input":0.4,"output":0.4,"cacheRead":null},"blendedRef":0.4305,"blendedMin":0.4,"blendedTrusted":0.4305,"spread":2.3,"hostCount":4,"pricedHostCount":4,"aa":{"idx":13.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-03-05","lastUpdated":"2025-03-05","url":"https://llmpricing.dev/m/alibaba/qwq-32b/"},{"id":"alibaba/qwen2.5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32768,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.287,"output":0.861,"cacheRead":null,"official":true},"cheapest":{"provider":"huggingface","input":0.06,"output":0.2,"cacheRead":null},"blendedRef":0.4305,"blendedMin":0.095,"blendedTrusted":0.095,"spread":11,"hostCount":8,"pricedHostCount":7,"aa":{"idx":6.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-11-12","lastUpdated":"2024-11-12","url":"https://llmpricing.dev/m/alibaba/qwen2.5-coder-32b-instruct/"},{"id":"alibaba/qwen3.8-27b","name":"Qwen3.8 27B","lab":"alibaba","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[262144,1000000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"kilo","input":0.575,"output":3.45,"cacheRead":0.115,"official":false},"cheapest":{"provider":"runinfra","input":0.1,"output":0.4,"cacheRead":0.01},"blendedRef":1.2938,"blendedMin":0.175,"blendedTrusted":1.05,"spread":5.7,"hostCount":14,"pricedHostCount":13,"aa":{"idx":52,"coding":68.1,"agentic":50.9,"speed":null,"ttft":null,"taskCost":null},"usage":{"rank":68,"tokens":28093612117,"share":0.00010528241989112268},"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/alibaba/qwen3.8-27b/"},{"id":"zhipuai/glm-4.7-flash","name":"GLM-4.7-Flash","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":[128000,203000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":{"provider":"crof","input":0.04,"output":0.3,"cacheRead":0.008},"blendedRef":0,"blendedMin":0.105,"blendedTrusted":0.145,"spread":2.5,"hostCount":24,"pricedHostCount":19,"aa":{"idx":23.3,"coding":null,"agentic":null,"speed":93,"ttft":1.24,"taskCost":null},"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flash/"},{"id":"mistral/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"cloudflare-ai-gateway","input":0.351,"output":0.555,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.3,"cacheRead":0.05},"blendedRef":0.402,"blendedMin":0.15,"blendedTrusted":0.402,"spread":3.5,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-03-18","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/mistral/mistral-small-3.1-24b-instruct/"},{"id":"ibm/granite-4-h-micro","name":"Granite-4.0-H-Micro","lab":"ibm","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudflare-ai-gateway","input":0.017,"output":0.112,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudflare-workers-ai","input":0.017,"output":0.112,"cacheRead":null},"blendedRef":0.0408,"blendedMin":0.0408,"blendedTrusted":0.0408,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-02","lastUpdated":"2025-10-02","url":"https://llmpricing.dev/m/ibm/granite-4-h-micro/"},{"id":"minimax/MiniMax-M2.1","name":"MiniMax-M2.1","lab":"minimax","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":[196000,1000000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"minimax-cn","input":0.3,"output":1.2,"cacheRead":0.03,"official":true},"cheapest":{"provider":"llmgateway","input":0.27,"output":1.1,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.4775,"blendedTrusted":0.525,"spread":7.8,"hostCount":23,"pricedHostCount":20,"aa":{"idx":32.1,"coding":null,"agentic":null,"speed":88,"ttft":1.88,"taskCost":null},"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/MiniMax-M2.1/"},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","lab":"deepseek","kind":"text","status":"deprecated","openWeights":true,"context":163840,"contextRange":[128000,164000],"outputLimit":81920,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf","image"],"reference":{"provider":"amazon-bedrock","input":0.62,"output":1.85,"cacheRead":null,"official":false},"cheapest":{"provider":"crof","input":0.18,"output":0.35,"cacheRead":0.04},"blendedRef":0.9275,"blendedMin":0.2225,"blendedTrusted":0.29,"spread":3.4,"hostCount":32,"pricedHostCount":29,"aa":{"idx":32.8,"coding":44.2,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":{"rank":27,"tokens":1712417922327,"share":0.00641738420736647},"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2/"},{"id":"deepseek/deepseek-v3.2-exp-2","name":"DeepSeek V3.2 Exp","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,164000],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.287,"output":0.431,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.22,"output":0.33,"cacheRead":null},"blendedRef":0.323,"blendedMin":0.2475,"blendedTrusted":0.323,"spread":1.3,"hostCount":7,"pricedHostCount":6,"aa":{"idx":25.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-10-10","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-exp-2/"},{"id":"alibaba/qwen3.5-plus","name":"Qwen3.5 Plus","lab":"alibaba","kind":"text","status":"deprecated","openWeights":false,"context":1000000,"contextRange":[262144,1000000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"alibaba-cn","input":0.573,"output":3.44,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":0.115,"output":0.688,"cacheRead":null},"blendedRef":1.2898,"blendedMin":0.2583,"blendedTrusted":0.9,"spread":7,"hostCount":15,"pricedHostCount":13,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-plus/"},{"id":"alibaba/qwen2.5-vl-32b-instruct","name":"Qwen2.5 VL 32B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":[16384,32000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"meganova","input":0.2,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"io-net","input":0.05,"output":0.22,"cacheRead":0.025},"blendedRef":0.3,"blendedMin":0.0925,"blendedTrusted":0.0925,"spread":4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-03-24","lastUpdated":"2025-03-24","url":"https://llmpricing.dev/m/alibaba/qwen2.5-vl-32b-instruct/"},{"id":"zhipuai/glm-4.6-2","name":"GLM-4.6","lab":"zhipuai","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":[198000,204800],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":0.6,"output":2.2,"cacheRead":0.11,"official":true},"cheapest":{"provider":"302ai","input":0.286,"output":1.142,"cacheRead":null},"blendedRef":1,"blendedMin":0.5,"blendedTrusted":0.7375,"spread":2.1,"hostCount":25,"pricedHostCount":22,"aa":{"idx":29.3,"coding":45.8,"agentic":18.6,"speed":50,"ttft":2.47,"taskCost":0.3046},"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-2/"},{"id":"zhipuai/glm-5-2","name":"GLM-5","lab":"zhipuai","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":[64000,205000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":1,"output":3.2,"cacheRead":0.2,"official":true},"cheapest":{"provider":"crof","input":0.48,"output":1.9,"cacheRead":0.1},"blendedRef":1.55,"blendedMin":0.835,"blendedTrusted":0.93,"spread":2.1,"hostCount":44,"pricedHostCount":38,"aa":{"idx":40.6,"coding":null,"agentic":null,"speed":46,"ttft":1.71,"taskCost":null},"usage":{"rank":55,"tokens":307060662375,"share":0.0011507274128216727},"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-2/"},{"id":"zhipuai/glm-4.7-2","name":"GLM-4.7","lab":"zhipuai","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":[128000,205000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf","image"],"reference":{"provider":"zai","input":0.6,"output":2.2,"cacheRead":0.11,"official":true},"cheapest":{"provider":"meganova","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":1,"blendedMin":0.35,"blendedTrusted":0.7375,"spread":17.5,"hostCount":38,"pricedHostCount":32,"aa":{"idx":34.5,"coding":45.3,"agentic":26.2,"speed":107,"ttft":0.96,"taskCost":0.3586},"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-2/"},{"id":"meta/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","lab":"meta","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":[16384,131072],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.05,"output":0.23,"cacheRead":0.025},"blendedRef":0,"blendedMin":0.095,"blendedTrusted":0.1925,"spread":58.4,"hostCount":36,"pricedHostCount":32,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct/"},{"id":"mistral/mistral-small-3.2-24b-instruct-2506","name":"Mistral Small 3.2 24B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[32768,256000],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.4,"cacheRead":0.1,"official":false},"cheapest":{"provider":"venice","input":0.09375,"output":0.25,"cacheRead":null},"blendedRef":0.25,"blendedMin":0.1328,"blendedTrusted":null,"spread":2.1,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/mistral/mistral-small-3.2-24b-instruct-2506/"},{"id":"mistral/mistral-nemo-instruct-2407","name":"Mistral Nemo Instruct 2407","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[65536,131072],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":0.145,"output":0.145,"cacheRead":0.014,"official":false},"cheapest":{"provider":"meganova","input":0.02,"output":0.04,"cacheRead":null},"blendedRef":0.145,"blendedMin":0.025,"blendedTrusted":0.025,"spread":7.2,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-11-20","url":"https://llmpricing.dev/m/mistral/mistral-nemo-instruct-2407/"},{"id":"openai/mini-lm-l12-v2","name":"All-MiniLM-L12-v2","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":128,"contextRange":null,"outputLimit":384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"infomaniak","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2021-08-30","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/openai/mini-lm-l12-v2/"},{"id":"openai/bge-multilingual-gemma2","name":"BGE Multilingual Gemma2","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":8191,"contextRange":[8000,8191],"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"scaleway","input":0.1,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"infomaniak","input":0.08,"output":0,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.06,"blendedTrusted":0.075,"spread":1.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-07-25","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/openai/bge-multilingual-gemma2/"},{"id":"nvidia/nvidia-nemotron-3-nano-30b-a3b-fp8","name":"Nemotron 3 Nano 30B A3B FP8","lab":"nvidia","kind":"text","status":"beta","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"infomaniak","input":0.06,"output":0.25,"cacheRead":null,"official":false},"cheapest":{"provider":"infomaniak","input":0.06,"output":0.25,"cacheRead":null},"blendedRef":0.1075,"blendedMin":0.1075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-3-nano-30b-a3b-fp8/"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","lab":"google","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":null,"cheapest":{"provider":"kilo","input":0.08,"output":0.35,"cacheRead":0.01},"blendedRef":null,"blendedMin":0.1475,"blendedTrusted":0.1925,"spread":12.4,"hostCount":29,"pricedHostCount":23,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it/"},{"id":"swiss-ai/apertus-v1.5-70b","name":"Apertus v1.5 70B","lab":"swiss-ai","kind":"text","status":"beta","openWeights":true,"context":100000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"infomaniak","input":0.87,"output":3.1,"cacheRead":null,"official":false},"cheapest":{"provider":"infomaniak","input":0.87,"output":3.1,"cacheRead":null},"blendedRef":1.4275,"blendedMin":1.4275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/swiss-ai/apertus-v1.5-70b/"},{"id":"alibaba/qwen3.5-122b-a10b-fp8","name":"Qwen3.5 122B-A10B FP8","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"infomaniak","input":0.5,"output":3.97,"cacheRead":null,"official":false},"cheapest":{"provider":"infomaniak","input":0.5,"output":3.97,"cacheRead":null},"blendedRef":1.3675,"blendedMin":1.3675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/alibaba/qwen3.5-122b-a10b-fp8/"},{"id":"mistral/ministral-3-14b-instruct-2512","name":"Ministral 3 14B Instruct","lab":"mistral","kind":"text","status":"beta","openWeights":true,"context":100000,"contextRange":null,"outputLimit":25600,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"infomaniak","input":0.37,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"infomaniak","input":0.37,"output":0.5,"cacheRead":null},"blendedRef":0.4025,"blendedMin":0.4025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/mistral/ministral-3-14b-instruct-2512/"},{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[32000,262144],"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":0.15,"output":0.6,"cacheRead":null,"official":true},"cheapest":{"provider":"cortecs","input":0.143,"output":0.568,"cacheRead":0.014},"blendedRef":0.2625,"blendedMin":0.2492,"blendedTrusted":0.2625,"spread":1.7,"hostCount":11,"pricedHostCount":11,"aa":{"idx":19.7,"coding":26.6,"agentic":4.6,"speed":160,"ttft":0.8,"taskCost":0.1003},"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/mistral/mistral-small-2603/"},{"id":"orcarouter/auto","name":"OrcaRouter Auto","lab":"orcarouter","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"orcarouter","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2026-05-14","url":"https://llmpricing.dev/m/orcarouter/auto/"},{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[128000,1000000],"outputLimit":384000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text"],"reference":{"provider":"deepseek","input":0.14,"output":0.28,"cacheRead":0.0028,"official":true},"cheapest":{"provider":"orcarouter","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":0.175,"spread":2.9,"hostCount":7,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2026-02-28","url":"https://llmpricing.dev/m/deepseek/deepseek-chat/"},{"id":"deepseek/deepseek-reasoner","name":"DeepSeek Reasoner","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[64000,1000000],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text"],"reference":{"provider":"deepseek","input":0.14,"output":0.28,"cacheRead":0.0028,"official":true},"cheapest":{"provider":"deepseek","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":0.175,"spread":4,"hostCount":7,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2026-02-28","url":"https://llmpricing.dev/m/deepseek/deepseek-reasoner/"},{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":0.25,"output":1.5,"cacheRead":0.025,"official":true},"cheapest":{"provider":"orcarouter","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":0.5625,"spread":1.2,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/google/gemini-flash-lite-latest/"},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":2,"output":12,"cacheRead":0.2,"official":true},"cheapest":{"provider":"requesty","input":1.8,"output":10.8,"cacheRead":0.18},"blendedRef":4.5,"blendedMin":4.05,"blendedTrusted":4.5,"spread":2.2,"hostCount":31,"pricedHostCount":30,"aa":{"idx":47.7,"coding":68.8,"agentic":23,"speed":108,"ttft":32.45,"taskCost":0.3346},"usage":{"rank":40,"tokens":754080825449,"share":0.002825961067808887},"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview/"},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1048576,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":2,"output":12,"cacheRead":0.2,"official":true},"cheapest":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":4.5,"spread":2,"hostCount":11,"pricedHostCount":11,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-customtools/"},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1048576,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":1.5,"output":9,"cacheRead":0.15,"official":true},"cheapest":{"provider":"nano-gpt","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":3.375,"blendedMin":1.5,"blendedTrusted":3.375,"spread":2,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-flash-latest/"},{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"orcarouter","input":4,"output":18,"cacheRead":0.2,"official":false},"cheapest":{"provider":"qihang-ai","input":0.57,"output":3.43,"cacheRead":null},"blendedRef":7.5,"blendedMin":1.285,"blendedTrusted":4.5,"spread":7,"hostCount":8,"pricedHostCount":7,"aa":{"idx":40.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-18","lastUpdated":"2025-11-18","url":"https://llmpricing.dev/m/google/gemini-3-pro-preview/"},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","lab":"google","kind":"text","status":"deprecated","openWeights":false,"context":1048576,"contextRange":[1048576,1050000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":0.25,"output":1.5,"cacheRead":0.025,"official":true},"cheapest":{"provider":"orcarouter","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":0.5625,"spread":1,"hostCount":12,"pricedHostCount":12,"aa":null,"usage":{"rank":24,"tokens":2114725004056,"share":0.007925053029993035},"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite-preview/"},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[256000,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google-vertex","input":0.5,"output":3,"cacheRead":0.05,"official":true},"cheapest":{"provider":"qihang-ai","input":0.07,"output":0.43,"cacheRead":null},"blendedRef":1.125,"blendedMin":0.16,"blendedTrusted":1.125,"spread":10,"hostCount":25,"pricedHostCount":24,"aa":{"idx":38.7,"coding":null,"agentic":null,"speed":161,"ttft":6.22,"taskCost":null},"usage":{"rank":16,"tokens":3926533163951,"share":0.014714907843173154},"releaseDate":"2025-12-17","lastUpdated":"2025-12-17","url":"https://llmpricing.dev/m/google/gemini-3-flash-preview/"},{"id":"anthropic/claude-opus-4-1","name":"Claude Opus 4.1 (latest)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"pioneer","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"requesty","input":13.5,"output":67.5,"cacheRead":1.35},"blendedRef":30,"blendedMin":27,"blendedTrusted":30,"spread":1.1,"hostCount":7,"pricedHostCount":7,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1/"},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[200000,1000000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":3,"output":15,"cacheRead":0.3,"official":true},"cheapest":{"provider":"xpersona","input":0.9,"output":5.55,"cacheRead":0.09},"blendedRef":6,"blendedMin":2.0625,"blendedTrusted":6,"spread":4,"hostCount":44,"pricedHostCount":42,"aa":{"idx":48.4,"coding":63,"agentic":42.1,"speed":55,"ttft":149.24,"taskCost":1.2182},"usage":{"rank":17,"tokens":3547068812263,"share":0.013292843459221843},"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-6/"},{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":1,"output":5,"cacheRead":0.1,"official":true},"cheapest":{"provider":"xpersona","input":0.6,"output":3.7,"cacheRead":0.06},"blendedRef":2,"blendedMin":1.375,"blendedTrusted":2,"spread":1.7,"hostCount":20,"pricedHostCount":17,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5/"},{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":5,"output":25,"cacheRead":0.5,"official":true},"cheapest":{"provider":"requesty","input":4.5,"output":22.5,"cacheRead":0.45},"blendedRef":10,"blendedMin":9,"blendedTrusted":10,"spread":1.2,"hostCount":15,"pricedHostCount":14,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-11-24","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5/"},{"id":"anthropic/claude-sonnet-4-0","name":"Claude Sonnet 4 (latest)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":216000,"contextRange":[200000,216000],"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"github-copilot","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"cortecs","input":2.898,"output":14.493,"cacheRead":0.29},"blendedRef":6,"blendedMin":5.7968,"blendedTrusted":6,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-0/"},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[200000,1000000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":5,"output":25,"cacheRead":0.5,"official":true},"cheapest":{"provider":"poe","input":4.3,"output":21,"cacheRead":0.43},"blendedRef":10,"blendedMin":8.475,"blendedTrusted":10,"spread":1.4,"hostCount":38,"pricedHostCount":36,"aa":{"idx":44.9,"coding":null,"agentic":null,"speed":39,"ttft":15.46,"taskCost":null},"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-6/"},{"id":"anthropic/claude-opus-4-0","name":"Claude Opus 4 (latest)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"orcarouter","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"orcarouter","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-0/"},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[200000,1000000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":3,"output":15,"cacheRead":0.3,"official":true},"cheapest":{"provider":"requesty","input":2.7,"output":13.5,"cacheRead":0.27},"blendedRef":6,"blendedMin":5.4,"blendedTrusted":6,"spread":1.1,"hostCount":17,"pricedHostCount":15,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5/"},{"id":"xai/grok-4.3","name":"Grok 4.3","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","video"],"reference":{"provider":"xai","input":1.25,"output":2.5,"cacheRead":0.2,"official":true},"cheapest":{"provider":"requesty","input":1.125,"output":2.25,"cacheRead":0.18},"blendedRef":1.5625,"blendedMin":1.4063,"blendedTrusted":1.5625,"spread":1.3,"hostCount":23,"pricedHostCount":22,"aa":{"idx":37.9,"coding":42.2,"agentic":24.2,"speed":118,"ttft":20.48,"taskCost":0.1454},"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/xai/grok-4.3/"},{"id":"openai/gpt-4o","name":"GPT-4o","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":2.5,"output":10,"cacheRead":1.25,"official":true},"cheapest":{"provider":"cloudflare-ai-gateway","input":1.25,"output":5,"cacheRead":0.625},"blendedRef":4.375,"blendedMin":2.1875,"blendedTrusted":2.1875,"spread":2.5,"hostCount":21,"pricedHostCount":20,"aa":{"idx":12.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-05-13","lastUpdated":"2024-08-06","url":"https://llmpricing.dev/m/openai/gpt-4o/"},{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,400000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.75,"output":14,"cacheRead":0.175,"official":true},"cheapest":{"provider":"orcarouter","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":4.8125,"spread":1,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/openai/gpt-5.3-chat-latest/"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.05,"output":0.4,"cacheRead":0.005,"official":true},"cheapest":{"provider":"jiekou","input":0.045,"output":0.36,"cacheRead":null},"blendedRef":0.1375,"blendedMin":0.1238,"blendedTrusted":0.1375,"spread":1.3,"hostCount":26,"pricedHostCount":25,"aa":{"idx":20.1,"coding":null,"agentic":null,"speed":167,"ttft":94.31,"taskCost":null},"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-nano/"},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":[124096,128000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.15,"output":0.6,"cacheRead":0.075,"official":true},"cheapest":{"provider":"cloudflare-ai-gateway","input":0.075,"output":0.3,"cacheRead":0.0375},"blendedRef":0.2625,"blendedMin":0.1312,"blendedTrusted":0.1312,"spread":2.5,"hostCount":20,"pricedHostCount":20,"aa":{"idx":6.7,"coding":11.4,"agentic":1,"speed":101,"ttft":1.03,"taskCost":null},"usage":{"rank":36,"tokens":923782746980,"share":0.0034619287349265536},"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/gpt-4o-mini/"},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":16385,"contextRange":[16384,16385],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.5,"output":1.5,"cacheRead":0,"official":true},"cheapest":{"provider":"poe","input":0.45,"output":1.4,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.6875,"blendedTrusted":0.75,"spread":1.1,"hostCount":12,"pricedHostCount":12,"aa":{"idx":3.2,"coding":10.7,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2023-03-01","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo/"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":[400000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":30,"output":180,"cacheRead":null,"official":true},"cheapest":{"provider":"requesty","input":27,"output":162,"cacheRead":null},"blendedRef":67.5,"blendedMin":60.75,"blendedTrusted":67.5,"spread":1.4,"hostCount":18,"pricedHostCount":18,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5-pro/"},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":10,"output":30,"cacheRead":null,"official":true},"cheapest":{"provider":"poe","input":9,"output":27,"cacheRead":null},"blendedRef":15,"blendedMin":13.5,"blendedTrusted":15,"spread":1.1,"hostCount":14,"pricedHostCount":14,"aa":{"idx":7.7,"coding":21.5,"agentic":null,"speed":32,"ttft":2.91,"taskCost":null},"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4-turbo/"},{"id":"openai/gpt-4","name":"GPT-4","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":8192,"contextRange":[8191,8192],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"openai","input":30,"output":60,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":30,"output":60,"cacheRead":null},"blendedRef":37.5,"blendedMin":37.5,"blendedTrusted":37.5,"spread":1,"hostCount":8,"pricedHostCount":8,"aa":{"idx":6.8,"coding":13.1,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4/"},{"id":"openai/gpt-5-chat-latest","name":"GPT-5 Chat (latest)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,400000],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"merge-gateway","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"jiekou","input":1.125,"output":9,"cacheRead":null},"blendedRef":3.4375,"blendedMin":3.0938,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-chat-latest/"},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":[1000000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":30,"output":180,"cacheRead":null,"official":true},"cheapest":{"provider":"poe","input":27,"output":160,"cacheRead":null},"blendedRef":67.5,"blendedMin":60.25,"blendedTrusted":67.5,"spread":2.2,"hostCount":18,"pricedHostCount":18,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-pro/"},{"id":"openai/gpt-5-2","name":"GPT-5","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.25,"output":10,"cacheRead":0.125,"official":true},"cheapest":{"provider":"opencode","input":1.07,"output":8.5,"cacheRead":0.107},"blendedRef":3.4375,"blendedMin":2.9275,"blendedTrusted":3.4375,"spread":1.3,"hostCount":28,"pricedHostCount":25,"aa":{"idx":35.3,"coding":37.8,"agentic":26.5,"speed":81,"ttft":98.85,"taskCost":0.2572},"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-2/"},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[256000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":0.25,"output":2,"cacheRead":0.03,"official":false},"cheapest":{"provider":"poe","input":0.22,"output":1.8,"cacheRead":0.022},"blendedRef":0.6875,"blendedMin":0.615,"blendedTrusted":0.6875,"spread":1.1,"hostCount":16,"pricedHostCount":16,"aa":{"idx":31.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex-mini/"},{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[256000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"opencode","input":1.07,"output":8.5,"cacheRead":0.107},"blendedRef":3.4375,"blendedMin":2.9275,"blendedTrusted":3.4375,"spread":1.2,"hostCount":11,"pricedHostCount":11,"aa":{"idx":37,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-15","lastUpdated":"2025-09-15","url":"https://llmpricing.dev/m/openai/gpt-5-codex/"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":400000,"contextRange":[200000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.25,"output":2,"cacheRead":0.025,"official":true},"cheapest":{"provider":"qihang-ai","input":0.04,"output":0.29,"cacheRead":null},"blendedRef":0.6875,"blendedMin":0.1025,"blendedTrusted":0.6875,"spread":7,"hostCount":31,"pricedHostCount":29,"aa":{"idx":31.6,"coding":null,"agentic":null,"speed":85,"ttft":12.91,"taskCost":null},"usage":{"rank":51,"tokens":441041027671,"share":0.001652826502732713},"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-mini/"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.75,"output":14,"cacheRead":0.175,"official":true},"cheapest":{"provider":"requesty","input":1.575,"output":12.6,"cacheRead":0.1575},"blendedRef":4.8125,"blendedMin":4.3313,"blendedTrusted":4.8125,"spread":1.4,"hostCount":27,"pricedHostCount":27,"aa":{"idx":45.5,"coding":null,"agentic":null,"speed":125,"ttft":74.62,"taskCost":null},"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/gpt-5.3-codex/"},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":1047576,"contextRange":[1000000,1047576],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.1,"output":0.4,"cacheRead":0.025,"official":true},"cheapest":{"provider":"sap-ai-core","input":0.08,"output":0.26,"cacheRead":null},"blendedRef":0.175,"blendedMin":0.125,"blendedTrusted":0.125,"spread":1.4,"hostCount":20,"pricedHostCount":20,"aa":{"idx":9.6,"coding":11.1,"agentic":1.2,"speed":125,"ttft":0.68,"taskCost":0.0349},"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-nano/"},{"id":"openai/gpt-5.2-2","name":"GPT-5.2","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[256000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.75,"output":14,"cacheRead":0.175,"official":true},"cheapest":{"provider":"qihang-ai","input":0.25,"output":2,"cacheRead":null},"blendedRef":4.8125,"blendedMin":0.6875,"blendedTrusted":3.2975,"spread":84,"hostCount":33,"pricedHostCount":31,"aa":{"idx":43.3,"coding":null,"agentic":null,"speed":78,"ttft":142.93,"taskCost":null},"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-2/"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[272000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.75,"output":4.5,"cacheRead":0.075,"official":true},"cheapest":{"provider":"xpersona","input":0.375,"output":4,"cacheRead":0.0375},"blendedRef":1.6875,"blendedMin":1.2813,"blendedTrusted":1.6875,"spread":2.5,"hostCount":36,"pricedHostCount":34,"aa":{"idx":40.9,"coding":56.1,"agentic":31.5,"speed":163,"ttft":11.89,"taskCost":0.4948},"usage":{"rank":56,"tokens":295368719160,"share":0.0011069111862083668},"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-mini/"},{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":5,"output":15,"cacheRead":null,"official":true},"cheapest":{"provider":"orcarouter","input":5,"output":15,"cacheRead":null},"blendedRef":7.5,"blendedMin":7.5,"blendedTrusted":7.5,"spread":1,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2024-05-13","lastUpdated":"2024-05-13","url":"https://llmpricing.dev/m/openai/gpt-4o-2024-05-13/"},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":272000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":15,"output":120,"cacheRead":null,"official":true},"cheapest":{"provider":"jiekou","input":13.5,"output":108,"cacheRead":null},"blendedRef":41.25,"blendedMin":37.125,"blendedTrusted":41.25,"spread":1.1,"hostCount":15,"pricedHostCount":15,"aa":null,"usage":null,"releaseDate":"2025-10-06","lastUpdated":"2025-10-06","url":"https://llmpricing.dev/m/openai/gpt-5-pro/"},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,400000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"venice","input":2.19,"output":17.5,"cacheRead":0.219,"official":false},"cheapest":{"provider":"qihang-ai","input":0.14,"output":1.14,"cacheRead":null},"blendedRef":6.0175,"blendedMin":0.39,"blendedTrusted":4.8125,"spread":15.6,"hostCount":21,"pricedHostCount":21,"aa":{"idx":41.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-codex/"},{"id":"openai/gpt-4.1","name":"GPT-4.1","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":1047576,"contextRange":[128000,1047576],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":2,"output":8,"cacheRead":0.5,"official":true},"cheapest":{"provider":"poe","input":1.8,"output":7.2,"cacheRead":0.45},"blendedRef":3.5,"blendedMin":3.15,"blendedTrusted":3.5,"spread":1.2,"hostCount":26,"pricedHostCount":23,"aa":{"idx":19.6,"coding":null,"agentic":null,"speed":142,"ttft":0.87,"taskCost":null},"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1/"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":2.5,"output":10,"cacheRead":1.25,"official":true},"cheapest":{"provider":"orcarouter","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":1,"hostCount":7,"pricedHostCount":7,"aa":null,"usage":null,"releaseDate":"2024-08-06","lastUpdated":"2024-08-06","url":"https://llmpricing.dev/m/openai/gpt-4o-2024-08-06/"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","audio"],"reference":{"provider":"openai","input":2.5,"output":10,"cacheRead":1.25,"official":true},"cheapest":{"provider":"orcarouter","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":1,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2024-11-20","lastUpdated":"2024-11-20","url":"https://llmpricing.dev/m/openai/gpt-4o-2024-11-20/"},{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.75,"output":14,"cacheRead":0.175,"official":true},"cheapest":{"provider":"orcarouter","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":4.8125,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-chat-latest/"},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":21,"output":168,"cacheRead":null,"official":true},"cheapest":{"provider":"poe","input":19,"output":150,"cacheRead":null},"blendedRef":57.75,"blendedMin":51.75,"blendedTrusted":57.75,"spread":1.1,"hostCount":10,"pricedHostCount":10,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-pro/"},{"id":"openai/gpt-5.1-chat-latest","name":"GPT-5.1 Chat","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"zenmux","input":1.25,"output":10,"cacheRead":0.12,"official":false},"cheapest":{"provider":"orcarouter","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-chat-latest/"},{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[256000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":2.5,"output":20,"cacheRead":0.25,"official":false},"cheapest":{"provider":"poe","input":1.1,"output":9,"cacheRead":0.11},"blendedRef":6.875,"blendedMin":3.075,"blendedTrusted":3.4375,"spread":2.3,"hostCount":14,"pricedHostCount":14,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex-max/"},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[272000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"abacus","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"opencode","input":1.07,"output":8.5,"cacheRead":0.107},"blendedRef":3.4375,"blendedMin":2.9275,"blendedTrusted":3.4375,"spread":1.2,"hostCount":17,"pricedHostCount":17,"aa":{"idx":35.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex/"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":1047576,"contextRange":[1000000,1047576],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.4,"output":1.6,"cacheRead":0.1,"official":true},"cheapest":{"provider":"poe","input":0.36,"output":1.4,"cacheRead":0.09},"blendedRef":0.7,"blendedMin":0.62,"blendedTrusted":0.7,"spread":1.2,"hostCount":23,"pricedHostCount":21,"aa":{"idx":14.8,"coding":20.2,"agentic":1.8,"speed":102,"ttft":0.93,"taskCost":0.0638},"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-mini/"},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[400000,1047576],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":0.2,"output":1.25,"cacheRead":0.02,"official":true},"cheapest":{"provider":"poe","input":0.18,"output":1.1,"cacheRead":0.018},"blendedRef":0.4625,"blendedMin":0.41,"blendedTrusted":0.4625,"spread":1.1,"hostCount":30,"pricedHostCount":29,"aa":{"idx":39.7,"coding":56.1,"agentic":29.7,"speed":185,"ttft":4.11,"taskCost":0.1493},"usage":{"rank":54,"tokens":319077244764,"share":0.0011957602433265622},"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-nano/"},{"id":"openai/gpt-5.1","name":"GPT-5.1","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","audio"],"reference":{"provider":"openai","input":1.25,"output":10,"cacheRead":0.125,"official":true},"cheapest":{"provider":"opencode","input":1.07,"output":8.5,"cacheRead":0.107},"blendedRef":3.4375,"blendedMin":2.9275,"blendedTrusted":3.4375,"spread":1.3,"hostCount":28,"pricedHostCount":26,"aa":{"idx":37.5,"coding":49.4,"agentic":21.6,"speed":112,"ttft":28.41,"taskCost":0.304},"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1/"},{"id":"alibaba/qwen3.6-plus","name":"Qwen3.6 Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[262144,1000000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"alibaba-cn","input":0.5,"output":3,"cacheRead":0.05,"official":true},"cheapest":{"provider":"merge-gateway","input":0.276,"output":1.651,"cacheRead":0.0552},"blendedRef":1.125,"blendedMin":0.6198,"blendedTrusted":1.125,"spread":7.2,"hostCount":27,"pricedHostCount":23,"aa":{"idx":40.5,"coding":54.5,"agentic":29,"speed":56,"ttft":2.2,"taskCost":0.3569},"usage":{"rank":62,"tokens":116435495001,"share":0.0004363486839596561},"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/alibaba/qwen3.6-plus/"},{"id":"minimax/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":[200000,204800],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"minimax-cn","input":0.6,"output":2.4,"cacheRead":0.06,"official":true},"cheapest":{"provider":"empiriolabs","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":1.05,"blendedMin":0.525,"blendedTrusted":1.05,"spread":2,"hostCount":16,"pricedHostCount":14,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/MiniMax-M2.7-highspeed/"},{"id":"minimax/MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"minimax-cn","input":0.6,"output":2.4,"cacheRead":0.06,"official":true},"cheapest":{"provider":"orcarouter","input":0.6,"output":2.4,"cacheRead":0.06},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":1.05,"spread":1,"hostCount":10,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2026-02-13","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/minimax/MiniMax-M2.5-highspeed/"},{"id":"minimax/MiniMax-M2.7","name":"MiniMax-M2.7","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":[192000,262100],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"minimax-cn","input":0.3,"output":1.2,"cacheRead":0.06,"official":true},"cheapest":{"provider":"llmgateway","input":0.08,"output":0.32,"cacheRead":0.017},"blendedRef":0.525,"blendedMin":0.14,"blendedTrusted":0.4375,"spread":10.2,"hostCount":42,"pricedHostCount":36,"aa":{"idx":38.9,"coding":52.6,"agentic":25.9,"speed":61,"ttft":1.75,"taskCost":0.0777},"usage":{"rank":42,"tokens":642078972591,"share":0.0024062277116256065},"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/MiniMax-M2.7/"},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":12.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-04-07","lastUpdated":"2025-04-07","url":"https://llmpricing.dev/m/nvidia/llama-3.3-nemotron-super-49b-v1/"},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32000,262144],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"deepinfra","input":0.05,"output":0.2,"cacheRead":0.025},"blendedRef":0,"blendedMin":0.0875,"blendedTrusted":0.0875,"spread":1.2,"hostCount":10,"pricedHostCount":7,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2025-12-15","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-30b-a3b/"},{"id":"nvidia/active-speaker-detection","name":"Active Speaker Detection","lab":"nvidia","kind":"classify","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/nvidia/active-speaker-detection/"},{"id":"nvidia/llama-3.1-nemotron-nano-8b-v1","name":"Llama 3.1 Nemotron Nano 8B v1","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-18","lastUpdated":"2025-03-18","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-nano-8b-v1/"},{"id":"nvidia/gliner-pii","name":"gliner-pii","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/nvidia/gliner-pii/"},{"id":"nvidia/nemotron-3-content-safety","name":"Nemotron 3 Content Safety","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/nvidia/nemotron-3-content-safety/"},{"id":"nvidia/cosmos-transfer2-5-2b","name":"cosmos-transfer2.5-2b","lab":"nvidia","kind":"video","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-02-26","url":"https://llmpricing.dev/m/nvidia/cosmos-transfer2-5-2b/"},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"edenai","input":0.6,"output":0.6,"cacheRead":null},"blendedRef":0,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-70b-instruct/"},{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"Nemotron Nano 12B v2 VL","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"digitalocean","input":0.2,"output":0.6,"cacheRead":null},"blendedRef":0,"blendedMin":0.3,"blendedTrusted":0.3,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-28","lastUpdated":"2025-10-28","url":"https://llmpricing.dev/m/nvidia/nemotron-nano-12b-v2-vl/"},{"id":"nvidia/nemotron-voicechat","name":"Nemotron VoiceChat","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/nvidia/nemotron-voicechat/"},{"id":"nvidia/studiovoice","name":"studiovoice","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-03","lastUpdated":"2025-06-13","url":"https://llmpricing.dev/m/nvidia/studiovoice/"},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"Llama Nemotron Rerank VL 1B v2","lab":"nvidia","kind":"rerank","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-31","lastUpdated":"2026-03-31","url":"https://llmpricing.dev/m/nvidia/llama-nemotron-rerank-vl-1b-v2/"},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","lab":"nvidia","kind":"text","status":"deprecated","openWeights":true,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"deepinfra","input":0.4,"output":0.4,"cacheRead":null},"blendedRef":0,"blendedMin":0.4,"blendedTrusted":0.4,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2025-07-25","url":"https://llmpricing.dev/m/nvidia/llama-3.3-nemotron-super-49b-v1.5/"},{"id":"nvidia/llama-3-2-nemoretriever-300m-embed-v1","name":"llama-3_2-nemoretriever-300m-embed-v1","lab":"nvidia","kind":"embedding","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-07-24","lastUpdated":"2025-07-24","url":"https://llmpricing.dev/m/nvidia/llama-3-2-nemoretriever-300m-embed-v1/"},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0.2,"output":0.8,"cacheRead":null,"official":true},"cheapest":{"provider":"nvidia","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":0.35,"spread":1,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-12","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b/"},{"id":"nvidia/nemotron-3-nano-omni","name":"Nemotron 3 Nano Omni","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[65536,300000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"requesty","input":0.054,"output":0.216,"cacheRead":0.054},"blendedRef":0,"blendedMin":0.0945,"blendedTrusted":0.105,"spread":9.3,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-05-20","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni/"},{"id":"nvidia/rerank-qa-mistral-4b","name":"rerank-qa-mistral-4b","lab":"nvidia","kind":"rerank","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-03-17","lastUpdated":"2025-01-17","url":"https://llmpricing.dev/m/nvidia/rerank-qa-mistral-4b/"},{"id":"nvidia/nv-embed-v1","name":"nv-embed-v1","lab":"nvidia","kind":"embedding","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-06-07","lastUpdated":"2025-07-22","url":"https://llmpricing.dev/m/nvidia/nv-embed-v1/"},{"id":"nvidia/cosmos-transfer1-7b","name":"cosmos-transfer1-7b","lab":"nvidia","kind":"video","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-13","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/nvidia/cosmos-transfer1-7b/"},{"id":"nvidia/streampetr","name":"streampetr","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/nvidia/streampetr/"},{"id":"nvidia/nv-embedcode-7b-v1","name":"nv-embedcode-7b-v1","lab":"nvidia","kind":"embedding","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-17","lastUpdated":"2025-05-29","url":"https://llmpricing.dev/m/nvidia/nv-embedcode-7b-v1/"},{"id":"nvidia/usdvalidate","name":"usdvalidate","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-07-24","lastUpdated":"2025-01-08","url":"https://llmpricing.dev/m/nvidia/usdvalidate/"},{"id":"nvidia/nemotron-content-safety-reasoning-4b","name":"Nemotron Content Safety Reasoning 4B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-22","lastUpdated":"2026-01-22","url":"https://llmpricing.dev/m/nvidia/nemotron-content-safety-reasoning-4b/"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[131072,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0.5,"output":2.5,"cacheRead":0.15,"official":true},"cheapest":{"provider":"routing-run","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":1,"blendedMin":0.1,"blendedTrusted":1,"spread":10,"hostCount":14,"pricedHostCount":11,"aa":{"idx":38.3,"coding":49.3,"agentic":27.5,"speed":132,"ttft":1.98,"taskCost":0.3827},"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-a55b/"},{"id":"nvidia/cosmos-predict1-5b","name":"cosmos-predict1-5b","lab":"nvidia","kind":"video","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-18","lastUpdated":"2025-03-18","url":"https://llmpricing.dev/m/nvidia/cosmos-predict1-5b/"},{"id":"nvidia/magpie-tts-zeroshot","name":"magpie-tts-zeroshot","lab":"nvidia","kind":"audio","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-06-12","url":"https://llmpricing.dev/m/nvidia/magpie-tts-zeroshot/"},{"id":"nvidia/nvidia-nemotron-nano-9b-v2","name":"nvidia-nemotron-nano-9b-v2","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"amazon-bedrock","input":0.06,"output":0.23,"cacheRead":null},"blendedRef":0,"blendedMin":0.1025,"blendedTrusted":0.1025,"spread":1,"hostCount":3,"pricedHostCount":2,"aa":{"idx":8.7,"coding":null,"agentic":null,"speed":186,"ttft":4.08,"taskCost":null},"usage":null,"releaseDate":"2025-08-18","lastUpdated":"2025-08-18","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-nano-9b-v2/"},{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B A3B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[8192,1048576],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"runinfra","input":0.05,"output":0.15,"cacheRead":null},"blendedRef":0,"blendedMin":0.075,"blendedTrusted":0.0875,"spread":10,"hostCount":8,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-lightning/"},{"id":"nvidia/riva-translate-4b-instruct-v1.1","name":"riva-translate-4b-instruct-v1_1","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-12","lastUpdated":"2025-12-12","url":"https://llmpricing.dev/m/nvidia/riva-translate-4b-instruct-v1.1/"},{"id":"nvidia/llama-3.1-nemotron-ultra-253b","name":"Llama 3.1 Nemotron Ultra 253B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"llmgateway","input":0.6,"output":1.8,"cacheRead":null},"blendedRef":0,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-07","lastUpdated":"2025-04-07","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-ultra-253b/"},{"id":"nvidia/sparsedrive","name":"sparsedrive","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-18","lastUpdated":"2025-07-20","url":"https://llmpricing.dev/m/nvidia/sparsedrive/"},{"id":"nvidia/usdcode","name":"usdcode","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-01","lastUpdated":"2026-01-01","url":"https://llmpricing.dev/m/nvidia/usdcode/"},{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","name":"Llama 3.1 Nemotron Safety Guard 8B v3","lab":"nvidia","kind":"classify","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-28","lastUpdated":"2025-10-28","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-safety-guard-8b-v3/"},{"id":"nvidia/bevformer","name":"bevformer","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-18","lastUpdated":"2025-07-20","url":"https://llmpricing.dev/m/nvidia/bevformer/"},{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/nvidia/cosmos-reason2-8b/"},{"id":"nvidia/llama-3.1-nemotron-nano-vl-8b-v1","name":"Llama 3.1 Nemotron Nano VL 8B v1","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-10","lastUpdated":"2025-04-10","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-nano-vl-8b-v1/"},{"id":"nvidia/nemotron-mini-4b-instruct","name":"Nemotron Mini 4B Instruct","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-21","lastUpdated":"2024-08-26","url":"https://llmpricing.dev/m/nvidia/nemotron-mini-4b-instruct/"},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"Llama Nemotron Embed VL 1B v2","lab":"nvidia","kind":"embedding","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-10","lastUpdated":"2026-02-10","url":"https://llmpricing.dev/m/nvidia/llama-nemotron-embed-vl-1b-v2/"},{"id":"nvidia/synthetic-video-detector","name":"synthetic-video-detector","lab":"nvidia","kind":"classify","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["video"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/nvidia/synthetic-video-detector/"},{"id":"microsoft/phi-4-multimodal-instruct","name":"Phi 4 Multimodal","lab":"microsoft","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image","audio"],"reference":{"provider":"azure-cognitive-services","input":0.08,"output":0.32,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.07,"output":0.11,"cacheRead":0.035},"blendedRef":0.14,"blendedMin":0.08,"blendedTrusted":0.14,"spread":1.1,"hostCount":4,"pricedHostCount":3,"aa":{"idx":4.2,"coding":null,"agentic":null,"speed":17,"ttft":0.88,"taskCost":null},"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/microsoft/phi-4-multimodal-instruct/"},{"id":"microsoft/phi-4-mini","name":"Phi-4-mini","lab":"microsoft","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure-cognitive-services","input":0.075,"output":0.3,"cacheRead":null,"official":true},"cheapest":{"provider":"azure-cognitive-services","input":0.075,"output":0.3,"cacheRead":null},"blendedRef":0.1312,"blendedMin":0.1312,"blendedTrusted":0.1312,"spread":2.3,"hostCount":4,"pricedHostCount":3,"aa":{"idx":5.7,"coding":3.8,"agentic":null,"speed":44,"ttft":0.86,"taskCost":null},"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2024-12-11","url":"https://llmpricing.dev/m/microsoft/phi-4-mini/"},{"id":"google/gemma-3n-e2b-it","name":"Gemma 3n E2b It","lab":"google","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-12","lastUpdated":"2025-06-12","url":"https://llmpricing.dev/m/google/gemma-3n-e2b-it/"},{"id":"google/google-paligemma","name":"paligemma","lab":"google","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-05-14","lastUpdated":"2024-08-26","url":"https://llmpricing.dev/m/google/google-paligemma/"},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","lab":"google","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.04,"output":0.08,"cacheRead":null},"blendedRef":0.2006,"blendedMin":0.05,"blendedTrusted":0.05,"spread":5,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/google/gemma-3-4b-it/"},{"id":"google/gemma-3n-e4b-it","name":"Gemma 3n E4b It","lab":"google","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-03","lastUpdated":"2025-06-03","url":"https://llmpricing.dev/m/google/gemma-3n-e4b-it/"},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","lab":"google","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":0.272,"output":0.272,"cacheRead":0.136,"official":false},"cheapest":{"provider":"nano-gpt","input":0.272,"output":0.272,"cacheRead":0.136},"blendedRef":0.272,"blendedMin":0.272,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/google/gemma-3-12b-it/"},{"id":"google/gemma-2-2b-it","name":"Gemma 2 2b It","lab":"google","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-07-16","lastUpdated":"2024-07-16","url":"https://llmpricing.dev/m/google/gemma-2-2b-it/"},{"id":"meta/esmfold","name":"esmfold","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-03-15","lastUpdated":"2025-06-12","url":"https://llmpricing.dev/m/meta/esmfold/"},{"id":"meta/llama-guard-4-12b","name":"Llama Guard 4 12B","lab":"meta","kind":"classify","status":"ga","openWeights":true,"context":1048576,"contextRange":[128000,1048576],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.18,"output":0.18,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.18,"output":0.18,"cacheRead":null},"blendedRef":0.18,"blendedMin":0.18,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/meta/llama-guard-4-12b/"},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"fireworks-ai","input":0.35,"output":1.5,"cacheRead":0.04,"official":false},"cheapest":{"provider":"empiriolabs","input":0.2,"output":0.8,"cacheRead":0.05},"blendedRef":0.6375,"blendedMin":0.35,"blendedTrusted":0.6375,"spread":1.7,"hostCount":12,"pricedHostCount":10,"aa":null,"usage":null,"releaseDate":"2026-08-10","lastUpdated":"2026-08-10","url":"https://llmpricing.dev/m/meta/muse-glimmer-30b/"},{"id":"meta/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[16000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"neon","input":0.15,"output":0.45,"cacheRead":null,"official":false},"cheapest":{"provider":"inference","input":0.025,"output":0.025,"cacheRead":null},"blendedRef":0.225,"blendedMin":0.025,"blendedTrusted":0.06,"spread":11,"hostCount":13,"pricedHostCount":12,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-8b-instruct/"},{"id":"meta/llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct","lab":"meta","kind":"text","status":"beta","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.72,"output":0.72,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.4,"output":0.4,"cacheRead":null},"blendedRef":0.72,"blendedMin":0.4,"blendedTrusted":0.72,"spread":1.8,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-70b-instruct/"},{"id":"meta/esm2-650m","name":"esm2-650m","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-29","lastUpdated":"2025-03-10","url":"https://llmpricing.dev/m/meta/esm2-650m/"},{"id":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16000,"contextRange":[16000,128000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"io-net","input":0.35,"output":0.4,"cacheRead":0.175,"official":false},"cheapest":{"provider":"io-net","input":0.35,"output":0.4,"cacheRead":0.175},"blendedRef":0.3625,"blendedMin":0.3625,"blendedTrusted":0.3625,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-90b-vision-instruct/"},{"id":"meta/llama-4-maverick-17b-128e-instruct","name":"Llama 4 Maverick 17B 128E Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":524288,"contextRange":[128000,524288],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"google-vertex","input":0.35,"output":1.15,"cacheRead":null,"official":false},"cheapest":{"provider":"io-net","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.55,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":2.3,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-01","lastUpdated":"2025-04-29","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-128e-instruct/"},{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","lab":"poolside","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"poolside","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":{"provider":"openrouter","input":0.06,"output":0.12,"cacheRead":0.03},"blendedRef":0,"blendedMin":0.075,"blendedTrusted":null,"spread":null,"hostCount":4,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-02","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/poolside/laguna-xs-2.1/"},{"id":"bytedance-seed/seed-oss-36b-instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.21,"output":0.57,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.21,"output":0.57,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":0.3,"spread":1,"hostCount":3,"pricedHostCount":2,"aa":{"idx":18.5,"coding":null,"agentic":null,"speed":30,"ttft":2.94,"taskCost":null},"usage":null,"releaseDate":"2025-09-04","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/bytedance-seed/seed-oss-36b-instruct/"},{"id":"openai/whisper-large-v3","name":"Whisper Large v3","lab":"openai","kind":"audio","status":"ga","openWeights":true,"context":448,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"privatemode-ai","input":0.01618,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"scaleway","input":0.003,"output":0,"cacheRead":null},"blendedRef":0.0121,"blendedMin":0.0023,"blendedTrusted":0.0023,"spread":5.4,"hostCount":4,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2023-09-01","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/whisper-large-v3/"},{"id":"stepfun/step-3.5-flash-2","name":"Step 3.5 Flash","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"stepfun-ai","input":0.1,"output":0.3,"cacheRead":0.02,"official":true},"cheapest":{"provider":"edenai","input":0.09,"output":0.3,"cacheRead":0.02},"blendedRef":0.15,"blendedMin":0.1425,"blendedTrusted":0.15,"spread":1.1,"hostCount":12,"pricedHostCount":9,"aa":{"idx":26,"coding":null,"agentic":null,"speed":224,"ttft":1.08,"taskCost":null},"usage":null,"releaseDate":"2026-01-29","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/stepfun/step-3.5-flash-2/"},{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"stepfun-ai","input":0.185,"output":1.11,"cacheRead":0.037,"official":true},"cheapest":{"provider":"requesty","input":0.18,"output":1.035,"cacheRead":0.036},"blendedRef":0.4163,"blendedMin":0.3938,"blendedTrusted":0.4163,"spread":1.1,"hostCount":16,"pricedHostCount":12,"aa":{"idx":30.9,"coding":39.6,"agentic":21.7,"speed":117,"ttft":2.74,"taskCost":0.0913},"usage":{"rank":13,"tokens":5752274591629,"share":0.021556978375110832},"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/stepfun/step-3.7-flash/"},{"id":"baai/bge-m3","name":"BGE M3","lab":"baai","kind":"embedding","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.02,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.02,"output":0,"cacheRead":null},"blendedRef":0.015,"blendedMin":0.015,"blendedTrusted":0.015,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/baai/bge-m3/"},{"id":"alibaba/qwen-image","name":"Qwen Image","lab":"alibaba","kind":"image","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"regolo-ai","input":0.5,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"regolo-ai","input":0.5,"output":2,"cacheRead":null},"blendedRef":0.875,"blendedMin":0.875,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/alibaba/qwen-image/"},{"id":"alibaba/qwen-image-edit","name":"Qwen Image Edit","lab":"alibaba","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-19","lastUpdated":"2025-08-19","url":"https://llmpricing.dev/m/alibaba/qwen-image-edit/"},{"id":"abacusai/dracarys-llama-3.1-70b-instruct","name":"dracarys-llama-3.1-70b-instruct","lab":"abacusai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-09-11","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/abacusai/dracarys-llama-3.1-70b-instruct/"},{"id":"thinkingmachines/inkling","name":"Inkling","lab":"thinkingmachines","kind":"video","status":"ga","openWeights":true,"context":65536,"contextRange":[65536,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"thinkingmachines","input":1.87,"output":4.68,"cacheRead":0.374,"official":true},"cheapest":{"provider":"deepinfra","input":0.95,"output":4.05,"cacheRead":0.16},"blendedRef":2.5725,"blendedMin":1.725,"blendedTrusted":1.725,"spread":3.9,"hostCount":21,"pricedHostCount":19,"aa":{"idx":42.3,"coding":52.1,"agentic":34.1,"speed":74,"ttft":1.82,"taskCost":0.3389},"usage":null,"releaseDate":"2026-07-15","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/thinkingmachines/inkling/"},{"id":"mistral/magistral-small-2506","name":"Magistral Small 2506","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[32768,128000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"io-net","input":0.5,"output":1.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"io-net","input":0.5,"output":1.5,"cacheRead":0.25},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":0.75,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/mistral/magistral-small-2506/"},{"id":"mistral/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[32768,127000],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.2,"output":0.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"ovhcloud","input":0.11,"output":0.11,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.11,"blendedTrusted":0.11,"spread":1.8,"hostCount":5,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-01","lastUpdated":"2025-05-26","url":"https://llmpricing.dev/m/mistral/mistral-7b-instruct-v0.3/"},{"id":"mistral/mistral-large-3-675b-instruct-2512","name":"Mistral Large 3 675B Instruct 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral-large-3-675b-instruct-2512/"},{"id":"nvidia/mistral-nemotron","name":"Mistral Nemotron","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-11","lastUpdated":"2025-06-12","url":"https://llmpricing.dev/m/nvidia/mistral-nemotron/"},{"id":"mistral/mistral-small-4-119b-2603","name":"mistral-small-4-119b-2603","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/mistral/mistral-small-4-119b-2603/"},{"id":"mistral/mixtral-8x7b-instruct","name":"Mistral: Mixtral 8x7B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2023-12-10","lastUpdated":"2026-03-15","url":"https://llmpricing.dev/m/mistral/mixtral-8x7b-instruct/"},{"id":"mistral/mistral-medium-2604","name":"Mistral Medium 3.5","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"mistral","input":1.5,"output":7.5,"cacheRead":null,"official":true},"cheapest":{"provider":"cortecs","input":1.671,"output":5.57,"cacheRead":null},"blendedRef":3,"blendedMin":2.6458,"blendedTrusted":3,"spread":1.4,"hostCount":11,"pricedHostCount":9,"aa":{"idx":30.4,"coding":46.9,"agentic":19.2,"speed":132,"ttft":2.28,"taskCost":0.4637},"usage":null,"releaseDate":"2026-04-29","lastUpdated":"2026-04-29","url":"https://llmpricing.dev/m/mistral/mistral-medium-2604/"},{"id":"mistral/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":13108,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"kilo","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-17","lastUpdated":"2024-04-17","url":"https://llmpricing.dev/m/mistral/mixtral-8x22b-instruct/"},{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[128000,131072],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"mistral","input":0.4,"output":2,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.4,"output":2,"cacheRead":0.2},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":1,"hostCount":9,"pricedHostCount":7,"aa":{"idx":12.5,"coding":null,"agentic":null,"speed":57,"ttft":1.47,"taskCost":null},"usage":null,"releaseDate":"2025-05-07","lastUpdated":"2025-05-07","url":"https://llmpricing.dev/m/mistral/mistral-medium-2505/"},{"id":"mistral/ministral-14b-instruct-2512","name":"Ministral 3 14B Instruct 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-14b-instruct-2512/"},{"id":"minimax/MiniMax-M3","name":"MiniMax-M3","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[262144,1048576],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"minimax-cn","input":0.3,"output":1.2,"cacheRead":0.06,"official":true},"cheapest":{"provider":"empiriolabs","input":0.225,"output":0.9,"cacheRead":0.045},"blendedRef":0.525,"blendedMin":0.3938,"blendedTrusted":0.4125,"spread":2.7,"hostCount":38,"pricedHostCount":32,"aa":{"idx":45.4,"coding":58.6,"agentic":36.1,"speed":90,"ttft":1.35,"taskCost":0.1387},"usage":{"rank":9,"tokens":7780911261771,"share":0.029159410444825985},"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/minimax/MiniMax-M3/"},{"id":"upstage/solar-10.7b-instruct","name":"solar-10.7b-instruct","lab":"upstage","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-06-05","lastUpdated":"2025-04-10","url":"https://llmpricing.dev/m/upstage/solar-10.7b-instruct/"},{"id":"sarvamai/sarvam-m","name":"sarvam-m","lab":"sarvamai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":2.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2025-07-25","url":"https://llmpricing.dev/m/sarvamai/sarvam-m/"},{"id":"black-forest-labs/flux-2-klein-4b","name":"FLUX.2 Klein 4B","lab":"black-forest-labs","kind":"image","status":"ga","openWeights":true,"context":128000,"contextRange":[40960,128000],"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["image","text"],"reference":{"provider":"nearai","input":1,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"nearai","input":1,"output":1,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-14","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/black-forest-labs/flux-2-klein-4b/"},{"id":"black-forest-labs/flux.1-dev","name":"FLUX.1-dev","lab":"black-forest-labs","kind":"image","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-01","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/black-forest-labs/flux.1-dev/"},{"id":"black-forest-labs/flux-1-schnell","name":"FLUX.1-schnell","lab":"black-forest-labs","kind":"image","status":"ga","openWeights":true,"context":77,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-01","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/black-forest-labs/flux-1-schnell/"},{"id":"black-forest-labs/flux-1-kontext-dev","name":"FLUX.1-Kontext-dev","lab":"black-forest-labs","kind":"image","status":"ga","openWeights":true,"context":40960,"contextRange":null,"outputLimit":40960,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nvidia","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-12","lastUpdated":"2025-08-12","url":"https://llmpricing.dev/m/black-forest-labs/flux-1-kontext-dev/"},{"id":"alibaba/qwen3.5-2b","name":"Qwen3.5 2B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.08,"output":0.16,"cacheRead":0.04,"official":false},"cheapest":{"provider":"requesty","input":0.018,"output":0.09,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.036,"blendedTrusted":null,"spread":4.4,"hostCount":3,"pricedHostCount":2,"aa":{"idx":7.4,"coding":2.9,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-2b/"},{"id":"alibaba/qwen3.5-0.8b","name":"Qwen3.5 0.8B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.06,"output":0.12,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.06,"output":0.12,"cacheRead":0.03},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":{"idx":5.2,"coding":0,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-0.8b/"},{"id":"alibaba/qwen3.5-4b","name":"Qwen3.5 4B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"empiriolabs","input":0.04,"output":0.07,"cacheRead":0.02},"blendedRef":0.125,"blendedMin":0.0475,"blendedTrusted":null,"spread":2.5,"hostCount":3,"pricedHostCount":2,"aa":{"idx":20.4,"coding":22.6,"agentic":null,"speed":30,"ttft":0.71,"taskCost":null},"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-4b/"},{"id":"alibaba/qwen3.6-27b","name":"Qwen3.6 27B","lab":"alibaba","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"alibaba","input":0.6,"output":3.6,"cacheRead":null,"official":true},"cheapest":{"provider":"crof","input":0.2,"output":1.5,"cacheRead":0.04},"blendedRef":1.35,"blendedMin":0.525,"blendedTrusted":0.5875,"spread":3,"hostCount":26,"pricedHostCount":24,"aa":{"idx":37.7,"coding":53.7,"agentic":27.5,"speed":55,"ttft":3.74,"taskCost":0.2918},"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/alibaba/qwen3.6-27b/"},{"id":"alibaba/qwen3-vl-plus","name":"Qwen3-VL Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"alibaba-cn","input":0.143353,"output":1.433525,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.143,"output":1.434,"cacheRead":0.0286},"blendedRef":0.4659,"blendedMin":0.4658,"blendedTrusted":0.4659,"spread":1.4,"hostCount":6,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-plus/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507-2","name":"Qwen3-235B-A22B-Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":81920,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"helicone","input":0.3,"output":2.9000000000000004,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.3,"output":2.9000000000000004,"cacheRead":null},"blendedRef":0.95,"blendedMin":0.95,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-01","lastUpdated":"2025-07-25","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507-2/"},{"id":"alibaba/qwen3-235b-a22b-instruct","name":"Qwen3 235B A22B Instruct","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google-vertex","input":0.22,"output":0.88,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":0.13,"output":0.6,"cacheRead":null},"blendedRef":0.385,"blendedMin":0.2475,"blendedTrusted":0.385,"spread":1.7,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-01","lastUpdated":"2025-08-13","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct/"},{"id":"alibaba/qwen3-coder-plus","name":"Qwen3 Coder Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[128000,1048576],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":1,"output":5,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.574,"output":2.294,"cacheRead":0.1148},"blendedRef":2,"blendedMin":1.004,"blendedTrusted":2,"spread":10.5,"hostCount":15,"pricedHostCount":12,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-plus/"},{"id":"misc/claudius","name":"Claudius","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"claudinio","input":3,"output":8,"cacheRead":0.9,"official":false},"cheapest":{"provider":"claudinio","input":3,"output":8,"cacheRead":0.9},"blendedRef":4.25,"blendedMin":4.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/misc/claudius/"},{"id":"misc/claudinio","name":"Claudinio","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"claudinio","input":0.5,"output":2,"cacheRead":0.15,"official":false},"cheapest":{"provider":"claudinio","input":0.5,"output":2,"cacheRead":0.15},"blendedRef":0.875,"blendedMin":0.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/misc/claudinio/"},{"id":"amazon/nova-pro-v1","name":"Nova Pro 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":5000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"cortecs","input":0.918,"output":3.671,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.8,"output":3.2,"cacheRead":null},"blendedRef":1.6063,"blendedMin":1.4,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/amazon/nova-pro-v1/"},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[200000,1048576],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":5,"output":25,"cacheRead":0.5,"official":true},"cheapest":{"provider":"unorouter","input":0.425,"output":2.125,"cacheRead":null},"blendedRef":10,"blendedMin":0.85,"blendedTrusted":10,"spread":23.5,"hostCount":41,"pricedHostCount":38,"aa":{"idx":57.3,"coding":74.3,"agentic":49.4,"speed":54,"ttft":22.3,"taskCost":2.0315},"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-8/"},{"id":"misc/qwen3guard-gen-8b","name":"qwen3guard-gen-8b","lab":"misc","kind":"classify","status":"ga","openWeights":false,"context":32000,"contextRange":[32000,32768],"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-04","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/misc/qwen3guard-gen-8b/"},{"id":"alibaba/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.216,"output":0.861,"cacheRead":null,"official":true},"cheapest":{"provider":"tensorx","input":0.06,"output":0.25,"cacheRead":0.015},"blendedRef":0.3772,"blendedMin":0.1075,"blendedTrusted":0.1175,"spread":7.5,"hostCount":19,"pricedHostCount":18,"aa":{"idx":13.6,"coding":null,"agentic":null,"speed":91,"ttft":2.54,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-30b-a3b-instruct/"},{"id":"misc/qwen3guard-gen-0.6b","name":"qwen3guard-gen-0.6b","lab":"misc","kind":"classify","status":"ga","openWeights":false,"context":32000,"contextRange":[32000,32768],"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-04","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/misc/qwen3guard-gen-0.6b/"},{"id":"zhipuai/glm-5v-turbo","name":"GLM-5V-Turbo","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[200000,202800],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":{"provider":"zai","input":1.2,"output":4,"cacheRead":0.24,"official":true},"cheapest":{"provider":"302ai","input":0.72,"output":3.2,"cacheRead":null},"blendedRef":1.9,"blendedMin":1.34,"blendedTrusted":1.9,"spread":6.9,"hostCount":14,"pricedHostCount":13,"aa":{"idx":35.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-04-01","url":"https://llmpricing.dev/m/zhipuai/glm-5v-turbo/"},{"id":"misc/mistral-medium-2508","name":"mistral-medium-2508","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.446,"output":2.228,"cacheRead":0.045,"official":false},"cheapest":{"provider":"cortecs","input":0.446,"output":2.228,"cacheRead":0.045},"blendedRef":0.8915,"blendedMin":0.8915,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-07","lastUpdated":"2024-08-07","url":"https://llmpricing.dev/m/misc/mistral-medium-2508/"},{"id":"mistral/mistral-small-3.2-24b-instruct-2506-2","name":"mistral-small-3.2-24b-instruct-2506","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":[32000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"berget","input":0.33,"output":0.33,"cacheRead":null,"official":false},"cheapest":{"provider":"ovhcloud","input":0.1,"output":0.31,"cacheRead":null},"blendedRef":0.33,"blendedMin":0.1525,"blendedTrusted":0.1525,"spread":3.3,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-05-26","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/mistral/mistral-small-3.2-24b-instruct-2506-2/"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":{"provider":"google-vertex","input":0.3,"output":2.5,"cacheRead":0.03,"official":true},"cheapest":{"provider":"requesty","input":0.27,"output":2.25,"cacheRead":0.027},"blendedRef":0.85,"blendedMin":0.765,"blendedTrusted":0.85,"spread":1.4,"hostCount":20,"pricedHostCount":20,"aa":{"idx":37.4,"coding":49.3,"agentic":27.2,"speed":332,"ttft":9.76,"taskCost":0.0965},"usage":{"rank":44,"tokens":606084590600,"share":0.0022713367042778974},"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-lite/"},{"id":"misc/voxtral-small-2507","name":"voxtral-small-2507","lab":"misc","kind":"audio","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"cortecs","input":0.111,"output":0.334,"cacheRead":0.011,"official":false},"cheapest":{"provider":"cortecs","input":0.111,"output":0.334,"cacheRead":0.011},"blendedRef":0.1668,"blendedMin":0.1668,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-02","lastUpdated":"2026-02-02","url":"https://llmpricing.dev/m/misc/voxtral-small-2507/"},{"id":"meta/llama-3.1-405b-instruct","name":"Llama 3.1 405B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":1.95,"output":1.95,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":1.95,"output":1.95,"cacheRead":null},"blendedRef":1.95,"blendedMin":1.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-405b-instruct/"},{"id":"misc/ministral-8b-2512","name":"ministral-8b-2512","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.167,"output":0.167,"cacheRead":0.017,"official":false},"cheapest":{"provider":"cortecs","input":0.167,"output":0.167,"cacheRead":0.017},"blendedRef":0.167,"blendedMin":0.167,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-03","url":"https://llmpricing.dev/m/misc/ministral-8b-2512/"},{"id":"alibaba/qwen3-coder-next","name":"Qwen3 Coder Next","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[131072,262144],"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.5,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.108,"output":0.675,"cacheRead":0.06},"blendedRef":0.675,"blendedMin":0.2498,"blendedTrusted":0.525,"spread":4.6,"hostCount":15,"pricedHostCount":13,"aa":{"idx":21.3,"coding":36.2,"agentic":8.9,"speed":128,"ttft":1.07,"taskCost":0.3371},"usage":null,"releaseDate":"2026-02-03","lastUpdated":"2026-02-03","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-next/"},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","lab":"anthropic","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":2,"output":10,"cacheRead":0.2,"official":true},"cheapest":{"provider":"unorouter","input":1.44,"output":7.2,"cacheRead":null},"blendedRef":4,"blendedMin":2.88,"blendedTrusted":4,"spread":2.1,"hostCount":32,"pricedHostCount":29,"aa":{"idx":55.3,"coding":71.5,"agentic":49.7,"speed":76,"ttft":184.48,"taskCost":1.7173},"usage":{"rank":15,"tokens":4532033106314,"share":0.016984053544709214},"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-5/"},{"id":"amazon/nova-2-lite","name":"Nova 2 Lite","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[128000,1000000],"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","video"],"reference":{"provider":"cortecs","input":0.373,"output":3.144,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.3,"output":2.5,"cacheRead":null},"blendedRef":1.0658,"blendedMin":0.85,"blendedTrusted":0.85,"spread":1.2,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-04","url":"https://llmpricing.dev/m/amazon/nova-2-lite/"},{"id":"misc/nova-micro-v1","name":"nova-micro-v1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.04,"output":0.159,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.04,"output":0.159,"cacheRead":null},"blendedRef":0.0698,"blendedMin":0.0698,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/misc/nova-micro-v1/"},{"id":"nvidia/nvidia-nemotron-3-nano-omni","name":"nvidia-nemotron-3-nano-omni","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,300000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"vultr","input":0.13,"output":0.38,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.059,"output":0.237,"cacheRead":null},"blendedRef":0.1925,"blendedMin":0.1035,"blendedTrusted":0.1925,"spread":2.2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-29","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-3-nano-omni/"},{"id":"misc/cosmos3-super-reasoner","name":"cosmos3-super-reasoner","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[256000,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.099,"output":0.296,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.1483,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/misc/cosmos3-super-reasoner/"},{"id":"swiss-ai/apertus-70b","name":"Apertus 70B","lab":"swiss-ai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":[30000,65536],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":1.393,"output":2.228,"cacheRead":null,"official":false},"cheapest":{"provider":"regolo-ai","input":0.46,"output":2.42,"cacheRead":null},"blendedRef":1.6018,"blendedMin":0.95,"blendedTrusted":null,"spread":3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-02","lastUpdated":"2025-09-02","url":"https://llmpricing.dev/m/swiss-ai/apertus-70b/"},{"id":"mistral/devstral-2512","name":"Devstral 2","lab":"mistral","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[200000,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"mistral","input":0.4,"output":2,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.4,"output":2,"cacheRead":0.04},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":1.4,"hostCount":10,"pricedHostCount":9,"aa":{"idx":19.2,"coding":31.3,"agentic":10.6,"speed":37,"ttft":1.5,"taskCost":0},"usage":null,"releaseDate":"2025-12-09","lastUpdated":"2025-12-09","url":"https://llmpricing.dev/m/mistral/devstral-2512/"},{"id":"nousresearch/hermes-4-70b","name":"Hermes 4 70B","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.13,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.129,"output":0.399,"cacheRead":null},"blendedRef":0.1975,"blendedMin":0.1965,"blendedTrusted":0.1975,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/nousresearch/hermes-4-70b/"},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[200000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"google-vertex","input":1.5,"output":9,"cacheRead":0.15,"official":true},"cheapest":{"provider":"unorouter","input":0.1857,"output":1.1142,"cacheRead":null},"blendedRef":3.375,"blendedMin":0.4178,"blendedTrusted":3.375,"spread":8.9,"hostCount":29,"pricedHostCount":29,"aa":{"idx":52,"coding":70.1,"agentic":39.7,"speed":171,"ttft":27.29,"taskCost":0.6934},"usage":{"rank":39,"tokens":781704837032,"share":0.002929483632812152},"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-3.5-flash/"},{"id":"zhipuai/glm-5-turbo","name":"GLM-5-Turbo","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[200000,202800],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":1.2,"output":4,"cacheRead":0.24,"official":true},"cheapest":{"provider":"302ai","input":0.72,"output":3.2,"cacheRead":null},"blendedRef":1.9,"blendedMin":1.34,"blendedTrusted":1.9,"spread":1.7,"hostCount":17,"pricedHostCount":15,"aa":{"idx":39.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/zhipuai/glm-5-turbo/"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":{"provider":"google-vertex","input":0.25,"output":1.5,"cacheRead":0.025,"official":true},"cheapest":{"provider":"requesty","input":0.225,"output":1.35,"cacheRead":0.0225},"blendedRef":0.5625,"blendedMin":0.5063,"blendedTrusted":0.5625,"spread":1.2,"hostCount":21,"pricedHostCount":20,"aa":{"idx":25.6,"coding":34.7,"agentic":6.5,"speed":303,"ttft":5.56,"taskCost":0.0432},"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite/"},{"id":"unsloth/gemma-3-27b-it","name":"gemma-3-27b-it","lab":"unsloth","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[110000,131000],"outputLimit":96000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":0.2992,"output":0.2992,"cacheRead":0.1496,"official":false},"cheapest":{"provider":"cortecs","input":0.099,"output":0.299,"cacheRead":null},"blendedRef":0.2992,"blendedMin":0.149,"blendedTrusted":0.15,"spread":3,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/unsloth/gemma-3-27b-it/"},{"id":"alibaba/qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[131072,256000],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"alibaba-cn","input":0.286705,"output":1.14682,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.286705,"output":1.14682,"cacheRead":null},"blendedRef":0.5017,"blendedMin":0.5017,"blendedTrusted":0.5017,"spread":2.4,"hostCount":3,"pricedHostCount":3,"aa":{"idx":20.9,"coding":null,"agentic":null,"speed":57,"ttft":2.82,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2026-01-13","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b/"},{"id":"misc/minicpm-v-4.5","name":"minicpm-v-4.5","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.658,"output":1.11,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.651,"output":1.097,"cacheRead":null},"blendedRef":0.771,"blendedMin":0.7625,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/misc/minicpm-v-4.5/"},{"id":"nousresearch/hermes-4-405b","name":"Hermes 4 405B","lab":"nousresearch","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[128000,131072],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.996,"output":2.989,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.4943,"blendedTrusted":1.5,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/nousresearch/hermes-4-405b/"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"mistral","input":0.5,"output":1.5,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.5,"output":1.5,"cacheRead":0.05},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":0.75,"spread":1.1,"hostCount":11,"pricedHostCount":10,"aa":{"idx":15.9,"coding":20.1,"agentic":5.5,"speed":48,"ttft":1.17,"taskCost":0.0806},"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral-large-2512/"},{"id":"minimax/MiniMax-M2","name":"MiniMax-M2","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":196608,"contextRange":[196608,1000000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"minimax-cn","input":0.3,"output":1.2,"cacheRead":null,"official":true},"cheapest":{"provider":"llmgateway","input":0.2,"output":1,"cacheRead":0.03},"blendedRef":0.525,"blendedMin":0.4,"blendedTrusted":0.525,"spread":2.1,"hostCount":18,"pricedHostCount":16,"aa":{"idx":28.9,"coding":null,"agentic":null,"speed":89,"ttft":1.56,"taskCost":null},"usage":null,"releaseDate":"2025-10-27","lastUpdated":"2025-10-27","url":"https://llmpricing.dev/m/minimax/MiniMax-M2/"},{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"llama-3.1-nemotron-ultra-253b-v1","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.6,"output":1.8,"cacheRead":0.06,"official":false},"cheapest":{"provider":"cortecs","input":0.598,"output":1.794,"cacheRead":null},"blendedRef":0.9,"blendedMin":0.897,"blendedTrusted":0.9,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":8.9,"coding":null,"agentic":null,"speed":48,"ttft":2.34,"taskCost":null},"usage":null,"releaseDate":"2025-04-07","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-ultra-253b-v1/"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"google-vertex","input":0.75,"output":3.75,"cacheRead":0.075,"official":true},"cheapest":{"provider":"cortecs","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":1.5,"spread":2.5,"hostCount":21,"pricedHostCount":21,"aa":{"idx":51.6,"coding":69.2,"agentic":40.5,"speed":199,"ttft":18.47,"taskCost":0.3442},"usage":{"rank":10,"tokens":6129209599683,"share":0.022969563898977696},"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.6-flash/"},{"id":"misc/ministral-3b-2512","name":"ministral-3b-2512","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.111,"output":0.111,"cacheRead":0.011,"official":false},"cheapest":{"provider":"cortecs","input":0.111,"output":0.111,"cacheRead":0.011},"blendedRef":0.111,"blendedMin":0.111,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-03","url":"https://llmpricing.dev/m/misc/ministral-3b-2512/"},{"id":"openai/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","lab":"openai","kind":"classify","status":"ga","openWeights":true,"context":128000,"contextRange":[4096,131072],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":0.179,"output":0.697,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.3085,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":1.2,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-10-29","lastUpdated":"2025-10-29","url":"https://llmpricing.dev/m/openai/gpt-oss-safeguard-120b/"},{"id":"misc/nova-lite-v1","name":"nova-lite-v1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":300000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"cortecs","input":0.069,"output":0.275,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.069,"output":0.275,"cacheRead":null},"blendedRef":0.1205,"blendedMin":0.1205,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/misc/nova-lite-v1/"},{"id":"misc/ministral-14b-2512","name":"ministral-14b-2512","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,256000],"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.33,"output":0.33,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.223,"output":0.223,"cacheRead":0.022},"blendedRef":0.33,"blendedMin":0.223,"blendedTrusted":null,"spread":1.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/misc/ministral-14b-2512/"},{"id":"misc/mixtral-8x7b-instruct-v0.1","name":"Mixtral 8x7B Instruct v0.1","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"cortecs","input":0.488,"output":0.758,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.488,"output":0.758,"cacheRead":null},"blendedRef":0.5555,"blendedMin":0.5555,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-12-11","lastUpdated":"2023-12-11","url":"https://llmpricing.dev/m/misc/mixtral-8x7b-instruct-v0.1/"},{"id":"misc/nemotron-nano-v2-12b","name":"nemotron-nano-v2-12b","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.24,"output":0.707,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.24,"output":0.707,"cacheRead":null},"blendedRef":0.3568,"blendedMin":0.3568,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-31","lastUpdated":"2025-10-31","url":"https://llmpricing.dev/m/misc/nemotron-nano-v2-12b/"},{"id":"mistral/codestral-2508","name":"Codestral 2508","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"cortecs","input":0.334,"output":1.003,"cacheRead":0.033,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.9,"cacheRead":0.15},"blendedRef":0.5013,"blendedMin":0.45,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-08-01","lastUpdated":"2025-08-01","url":"https://llmpricing.dev/m/mistral/codestral-2508/"},{"id":"mistral/pixtral-12b-2409","name":"pixtral-12b-2409","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.223,"output":0.223,"cacheRead":null,"official":false},"cheapest":{"provider":"scaleway","input":0.2,"output":0.2,"cacheRead":null},"blendedRef":0.223,"blendedMin":0.2,"blendedTrusted":0.2,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-11-09","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/mistral/pixtral-12b-2409/"},{"id":"misc/mistral-7b-instruct-v0.2","name":"mistral-7b-instruct-v0.2","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"cortecs","input":0.159,"output":0.219,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.159,"output":0.219,"cacheRead":null},"blendedRef":0.174,"blendedMin":0.174,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-26","lastUpdated":"2025-05-26","url":"https://llmpricing.dev/m/misc/mistral-7b-instruct-v0.2/"},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":5,"output":25,"cacheRead":0.5,"official":true},"cheapest":{"provider":"requesty","input":4.5,"output":22.5,"cacheRead":0.45},"blendedRef":10,"blendedMin":9,"blendedTrusted":10,"spread":2.2,"hostCount":28,"pricedHostCount":27,"aa":{"idx":63.1,"coding":78,"agentic":59.2,"speed":53,"ttft":59.97,"taskCost":2.3369},"usage":{"rank":11,"tokens":6065054017305,"share":0.022729137180827315},"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/claude-opus-5/"},{"id":"mistral/pixtral-large-2502","name":"pixtral-large-2502","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2,"output":6,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":1.993,"output":5.978,"cacheRead":null},"blendedRef":3,"blendedMin":2.9893,"blendedTrusted":3,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-26","lastUpdated":"2025-05-26","url":"https://llmpricing.dev/m/mistral/pixtral-large-2502/"},{"id":"misc/mistral-large-2402","name":"mistral-large-2402","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"cortecs","input":4.284,"output":12.952,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":4.284,"output":12.952,"cacheRead":null},"blendedRef":6.451,"blendedMin":6.451,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-26","lastUpdated":"2025-05-26","url":"https://llmpricing.dev/m/misc/mistral-large-2402/"},{"id":"misc/mistral-small-2503","name":"mistral-small-2503","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cortecs","input":0.111,"output":0.334,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.111,"output":0.334,"cacheRead":null},"blendedRef":0.1668,"blendedMin":0.1668,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-20","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/misc/mistral-small-2503/"},{"id":"misc/nvidia-nemotron-3-nano-30b-a3b","name":"nvidia-nemotron-3-nano-30b-a3b","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cortecs","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"cortecs","input":0.06,"output":0.24,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":14.5,"coding":14.4,"agentic":2,"speed":230,"ttft":1.09,"taskCost":0.0249},"usage":null,"releaseDate":"2026-01-12","lastUpdated":"2026-01-12","url":"https://llmpricing.dev/m/misc/nvidia-nemotron-3-nano-30b-a3b/"},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":{"provider":"google-vertex","input":0.75,"output":3.75,"cacheRead":0.075,"official":true},"cheapest":{"provider":"nano-gpt","input":0.375,"output":1.875,"cacheRead":0.0375},"blendedRef":1.5,"blendedMin":0.75,"blendedTrusted":1.5,"spread":5,"hostCount":21,"pricedHostCount":21,"aa":{"idx":56,"coding":76.1,"agentic":45.1,"speed":323,"ttft":15.15,"taskCost":0.4022},"usage":{"rank":31,"tokens":1350622771790,"share":0.005061536166367893},"releaseDate":"2026-08-13","lastUpdated":"2026-08-13","url":"https://llmpricing.dev/m/google/gemini-3.7-flash/"},{"id":"alibaba/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[262144,1048576],"outputLimit":1010000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"merge-gateway","input":2.5,"output":6.25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"requesty","input":1.8,"output":5.4,"cacheRead":0.18},"blendedRef":3.4375,"blendedMin":2.7,"blendedTrusted":3,"spread":1.4,"hostCount":10,"pricedHostCount":10,"aa":{"idx":57.7,"coding":71.9,"agentic":57.1,"speed":46,"ttft":2.65,"taskCost":1.0919},"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/alibaba/qwen3.8-2.4t-a95b/"},{"id":"google/gemini-exp-1206","name":"Gemini 2.0 Pro 1206","lab":"google","kind":"text","status":"ga","openWeights":false,"context":2097152,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":1.258,"output":4.998,"cacheRead":0.629,"official":false},"cheapest":{"provider":"nano-gpt","input":1.258,"output":4.998,"cacheRead":0.629},"blendedRef":2.193,"blendedMin":2.193,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/google/gemini-exp-1206/"},{"id":"anthropic/claude-sonnet-4-5-20250929-thinking","name":"Claude Sonnet 4.5 Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-20250929-thinking/"},{"id":"google/gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.015},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":15.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-preview-06-17/"},{"id":"anthropic/claude-opus-4-20250514","name":"Claude 4 Opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":31.7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-20250514/"},{"id":"google/gemini-2.5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 0506","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":[1048576,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":0.25,"official":false},"cheapest":{"provider":"openrouter","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":4.375,"blendedMin":3.4375,"blendedTrusted":null,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-06","lastUpdated":"2025-05-07","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-preview-05-06/"},{"id":"misc/auto-model","name":"Auto model","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/misc/auto-model/"},{"id":"misc/claw-low","name":"Claw Low","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"nano-gpt","input":0.25,"output":1.5,"cacheRead":0.025,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/misc/claw-low/"},{"id":"misc/jamba-large-1.6","name":"Jamba Large 1.6","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.989,"output":7.99,"cacheRead":0.9945,"official":false},"cheapest":{"provider":"nano-gpt","input":1.989,"output":7.99,"cacheRead":0.9945},"blendedRef":3.4893,"blendedMin":3.4893,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/misc/jamba-large-1.6/"},{"id":"zhipuai/glm-4-air-0111","name":"GLM 4 Air 0111","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1394,"output":0.1394,"cacheRead":0.0697,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1394,"output":0.1394,"cacheRead":0.0697},"blendedRef":0.1394,"blendedMin":0.1394,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-11","lastUpdated":"2025-01-11","url":"https://llmpricing.dev/m/zhipuai/glm-4-air-0111/"},{"id":"anthropic/claude-opus-4-thinking-32000","name":"Claude 4 Opus Thinking (32K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-thinking-32000/"},{"id":"misc/doubao-1.5-vision-pro-32k","name":"Doubao 1.5 Vision Pro 32k","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.459,"output":1.377,"cacheRead":0.2295,"official":false},"cheapest":{"provider":"nano-gpt","input":0.459,"output":1.377,"cacheRead":0.2295},"blendedRef":0.6885,"blendedMin":0.6885,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-20","lastUpdated":"2025-01-22","url":"https://llmpricing.dev/m/misc/doubao-1.5-vision-pro-32k/"},{"id":"misc/celeris-1","name":"Celeris 1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":1,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":1},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":12.4,"coding":14.4,"agentic":2.4,"speed":1596,"ttft":0.63,"taskCost":0.2582},"usage":null,"releaseDate":"2026-07-25","lastUpdated":"2026-07-25","url":"https://llmpricing.dev/m/misc/celeris-1/"},{"id":"alibaba/qwen3.7-max","name":"Qwen3.7 Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[256000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":2.5,"output":7.5,"cacheRead":0.5,"official":true},"cheapest":{"provider":"merge-gateway","input":0.825,"output":2.4755,"cacheRead":0.165},"blendedRef":3.75,"blendedMin":1.2376,"blendedTrusted":1.875,"spread":3.6,"hostCount":30,"pricedHostCount":28,"aa":{"idx":46.7,"coding":66,"agentic":30.9,"speed":201,"ttft":2.26,"taskCost":0.5413},"usage":{"rank":60,"tokens":144292081676,"share":0.0005407428374361364},"releaseDate":"2026-05-21","lastUpdated":"2026-05-21","url":"https://llmpricing.dev/m/alibaba/qwen3.7-max/"},{"id":"google/gemma-4-31b-garnetv2","name":"Gemma 4 31B Garnet V2","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/google/gemma-4-31b-garnetv2/"},{"id":"google/gemini-3-pro-image-preview","name":"Gemini 3 Pro Image","lab":"google","kind":"image","status":"ga","openWeights":false,"context":65536,"contextRange":[65536,1048756],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"merge-gateway","input":2,"output":12,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-20","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/google/gemini-3-pro-image-preview/"},{"id":"google/gemma-4-31b-queen","name":"Gemma 4 31B Queen","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/google/gemma-4-31b-queen/"},{"id":"cognitivecomputations/venice-uncensored","name":"Venice Uncensored","lab":"cognitivecomputations","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":0.4,"cacheRead":0.2,"official":false},"cheapest":{"provider":"kilo","input":0.2,"output":0.9,"cacheRead":null},"blendedRef":0.4,"blendedMin":0.375,"blendedTrusted":null,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-01","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/cognitivecomputations/venice-uncensored/"},{"id":"google/gemini-2.5-flash-preview-04-17-thinking","name":"Gemini 2.5 Flash Preview Thinking","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":0.15,"output":3.5,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":3.5,"cacheRead":0.015},"blendedRef":0.9875,"blendedMin":0.9875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-17","lastUpdated":"2025-04-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-04-17-thinking/"},{"id":"deepseek/deepseek-v3-0324-2","name":"DeepSeek Chat 0324","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.77,"cacheRead":0.135,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.77,"cacheRead":0.135},"blendedRef":0.3425,"blendedMin":0.3425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-24","lastUpdated":"2025-03-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v3-0324-2/"},{"id":"zhipuai/glm-4-airx","name":"GLM-4 AirX","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.006,"output":2.006,"cacheRead":1.003,"official":false},"cheapest":{"provider":"nano-gpt","input":2.006,"output":2.006,"cacheRead":1.003},"blendedRef":2.006,"blendedMin":2.006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-06-05","url":"https://llmpricing.dev/m/zhipuai/glm-4-airx/"},{"id":"google/gemma-4-12b-it","name":"Gemma 4 12B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nano-gpt","input":0.06,"output":0.3,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.06,"output":0.3,"cacheRead":0.03},"blendedRef":0.12,"blendedMin":0.12,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-01","lastUpdated":"2026-08-01","url":"https://llmpricing.dev/m/google/gemma-4-12b-it/"},{"id":"misc/brave-pro","name":"Brave (Pro)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":5,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":5,"cacheRead":null},"blendedRef":5,"blendedMin":5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-10","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/brave-pro/"},{"id":"google/gemini-2.5-flash-preview-09-2025","name":"Gemini 2.5 Flash Preview (09/2025)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"302ai","input":0.3,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-26","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-09-2025/"},{"id":"google/gemini-2.5-flash-lite-preview-09-2025","name":"gemini-2.5-flash-lite-preview-09-2025","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":{"provider":"302ai","input":0.1,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.09,"output":0.36,"cacheRead":null},"blendedRef":0.175,"blendedMin":0.1575,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-preview-09-2025/"},{"id":"openai/azure-o3-mini","name":"Azure o3-mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-01-31","url":"https://llmpricing.dev/m/openai/azure-o3-mini/"},{"id":"meta/meta-llama-3-1-8b-instruct-fp8","name":"Llama 3.1 8B (decentralized)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.02,"output":0.03,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.02,"output":0.03,"cacheRead":0.01},"blendedRef":0.0225,"blendedMin":0.0225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/meta-llama-3-1-8b-instruct-fp8/"},{"id":"anthropic/claude-sonnet-4-thinking-1024","name":"Claude 4 Sonnet Thinking (1K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-thinking-1024/"},{"id":"misc/perplexity-academic-researcher","name":"Perplexity Academic Researcher","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":127000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2,"output":8,"cacheRead":1,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":8,"cacheRead":1},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-10","lastUpdated":"2026-07-10","url":"https://llmpricing.dev/m/misc/perplexity-academic-researcher/"},{"id":"misc/jamba-mini-1.7","name":"Jamba Mini 1.7","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1989,"output":0.408,"cacheRead":0.09945,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1989,"output":0.408,"cacheRead":0.09945},"blendedRef":0.2512,"blendedMin":0.2512,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/misc/jamba-mini-1.7/"},{"id":"perplexity/sonar-deep-research","name":"Perplexity Deep Research","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":60000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":3.4,"output":13.6,"cacheRead":1.7,"official":false},"cheapest":{"provider":"nano-gpt","input":3.4,"output":13.6,"cacheRead":1.7},"blendedRef":5.95,"blendedMin":5.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-deep-research/"},{"id":"google/gemini-2.5-pro-exp-03-25","name":"Gemini 2.5 Pro Experimental 0325","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":0.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-25","lastUpdated":"2025-03-25","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-exp-03-25/"},{"id":"alibaba/qwen3.8-max-thinking","name":"Qwen3.8 Max Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":991000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":0.25},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-03","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/alibaba/qwen3.8-max-thinking/"},{"id":"google/learnlm-1.5-pro-experimental","name":"Gemini LearnLM Experimental","lab":"google","kind":"text","status":"ga","openWeights":false,"context":32767,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":3.502,"output":10.506,"cacheRead":1.751,"official":false},"cheapest":{"provider":"nano-gpt","input":3.502,"output":10.506,"cacheRead":1.751},"blendedRef":5.253,"blendedMin":5.253,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-05-14","url":"https://llmpricing.dev/m/google/learnlm-1.5-pro-experimental/"},{"id":"zhipuai/glm-4.1v-thinking-flashx","name":"GLM 4.1V Thinking FlashX","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":64000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/zhipuai/glm-4.1v-thinking-flashx/"},{"id":"openai/azure-o1","name":"Azure o1","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":15,"output":60,"cacheRead":7.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":60,"cacheRead":7.5},"blendedRef":26.25,"blendedMin":26.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-17","url":"https://llmpricing.dev/m/openai/azure-o1/"},{"id":"zhipuai/glm-z1-air","name":"GLM Z1 Air","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.07,"output":0.07,"cacheRead":0.035,"official":false},"cheapest":{"provider":"nano-gpt","input":0.07,"output":0.07,"cacheRead":0.035},"blendedRef":0.07,"blendedMin":0.07,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/zhipuai/glm-z1-air/"},{"id":"alibaba/qwen3.5-omni-flash","name":"Qwen3.5 Omni Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":49152,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nano-gpt","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":19.2,"coding":null,"agentic":null,"speed":238,"ttft":1.81,"taskCost":null},"usage":null,"releaseDate":"2026-03-30","lastUpdated":"2026-03-30","url":"https://llmpricing.dev/m/alibaba/qwen3.5-omni-flash/"},{"id":"anthropic/claude-opus-4-1-thinking","name":"Claude 4.1 Opus Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-thinking/"},{"id":"deepseek/deepseek-reasoner-cheaper","name":"Deepseek R1 Cheaper","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":1.7,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.7,"cacheRead":0.2},"blendedRef":0.725,"blendedMin":0.725,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-01-20","url":"https://llmpricing.dev/m/deepseek/deepseek-reasoner-cheaper/"},{"id":"misc/qwen3-vl-235b-a22b-instruct-original","name":"Qwen3 VL 235B A22B Instruct Original","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.5,"output":1.2,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":1.2,"cacheRead":0.25},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/misc/qwen3-vl-235b-a22b-instruct-original/"},{"id":"alibaba/qwen-max","name":"Qwen 2.5 Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.5997,"output":6.392,"cacheRead":0.79985,"official":false},"cheapest":{"provider":"nano-gpt","input":1.5997,"output":6.392,"cacheRead":0.79985},"blendedRef":2.7978,"blendedMin":2.7978,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":10.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-04-03","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-max/"},{"id":"perplexity/sonar","name":"Perplexity Simple","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":127000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":1,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":1,"cacheRead":0.5},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar/"},{"id":"zhipuai/glm-4-long","name":"GLM-4 Long","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003},"blendedRef":0.2006,"blendedMin":0.2006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-08-01","url":"https://llmpricing.dev/m/zhipuai/glm-4-long/"},{"id":"google/gemini-2.5-flash-preview-05-20","name":"Gemini 2.5 Flash 0520","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.015},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-05-20/"},{"id":"meituan/longcat-2.0-thinking","name":"LongCat 2.0 Thinking","lab":"meituan","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.75,"output":3,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.75,"output":3,"cacheRead":0.015},"blendedRef":1.3125,"blendedMin":1.3125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/meituan/longcat-2.0-thinking/"},{"id":"alibaba/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[32768,131072],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.5,"output":6,"cacheRead":0.25,"official":false},"cheapest":{"provider":"merge-gateway","input":0.287,"output":2.867,"cacheRead":0.0574},"blendedRef":1.875,"blendedMin":0.932,"blendedTrusted":1.7225,"spread":3.4,"hostCount":9,"pricedHostCount":9,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-thinking/"},{"id":"alibaba/qwen3.5-flash","name":"Qwen3.5 Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[991808,1020000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"alibaba-cn","input":0.172,"output":1.72,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.029,"output":0.287,"cacheRead":0.0058},"blendedRef":0.559,"blendedMin":0.0935,"blendedTrusted":0.175,"spread":5.9,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-flash/"},{"id":"zhipuai/glm-zero-preview","name":"GLM Zero Preview","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.802,"output":1.802,"cacheRead":0.901,"official":false},"cheapest":{"provider":"nano-gpt","input":1.802,"output":1.802,"cacheRead":0.901},"blendedRef":1.802,"blendedMin":1.802,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-20","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/zhipuai/glm-zero-preview/"},{"id":"google/gemini-2.5-pro-preview-03-25","name":"Gemini 2.5 Pro Preview 0325","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":0.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-25","lastUpdated":"2025-03-25","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-preview-03-25/"},{"id":"misc/jamba-mini","name":"Jamba Mini","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1989,"output":0.408,"cacheRead":0.09945,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1989,"output":0.408,"cacheRead":0.09945},"blendedRef":0.2512,"blendedMin":0.2512,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/misc/jamba-mini/"},{"id":"misc/yi-lightning","name":"Yi Lightning","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":12000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003},"blendedRef":0.2006,"blendedMin":0.2006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-15","lastUpdated":"2024-10-16","url":"https://llmpricing.dev/m/misc/yi-lightning/"},{"id":"google/gemini-2.5-flash-preview-09-2025-thinking","name":"Gemini 2.5 Flash Preview (09/2025) – Thinking","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"nano-gpt","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-09-2025-thinking/"},{"id":"zhipuai/glm-4.1v-thinking-flash","name":"GLM 4.1V Thinking Flash","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":64000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/zhipuai/glm-4.1v-thinking-flash/"},{"id":"alibaba/qwen-plus","name":"Qwen Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[131072,1000000],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.115,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.115,"output":0.287,"cacheRead":null},"blendedRef":0.158,"blendedMin":0.158,"blendedTrusted":0.158,"spread":3.5,"hostCount":10,"pricedHostCount":10,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2025-09-11","url":"https://llmpricing.dev/m/alibaba/qwen-plus/"},{"id":"misc/mercury-coder-small","name":"Mercury Coder Small","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.25,"output":1,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":1,"cacheRead":0.125},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/mercury-coder-small/"},{"id":"misc/jamba-large-1.7","name":"Jamba Large 1.7","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.989,"output":7.99,"cacheRead":0.9945,"official":false},"cheapest":{"provider":"nano-gpt","input":1.989,"output":7.99,"cacheRead":0.9945},"blendedRef":3.4893,"blendedMin":3.4893,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/misc/jamba-large-1.7/"},{"id":"misc/doubao-1.5-pro-256k","name":"Doubao 1.5 Pro 256k","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.799,"output":1.445,"cacheRead":0.3995,"official":false},"cheapest":{"provider":"nano-gpt","input":0.799,"output":1.445,"cacheRead":0.3995},"blendedRef":0.9605,"blendedMin":0.9605,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/misc/doubao-1.5-pro-256k/"},{"id":"misc/holo3-35b-a3b-thinking","name":"Holo3-35B-A3B Thinking","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.25,"output":1.8,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":1.8,"cacheRead":0.125},"blendedRef":0.6375,"blendedMin":0.6375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/holo3-35b-a3b-thinking/"},{"id":"misc/baichuan4-air","name":"Baichuan 4 Air","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.157,"output":0.157,"cacheRead":0.0785,"official":false},"cheapest":{"provider":"nano-gpt","input":0.157,"output":0.157,"cacheRead":0.0785},"blendedRef":0.157,"blendedMin":0.157,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-19","lastUpdated":"2025-08-19","url":"https://llmpricing.dev/m/misc/baichuan4-air/"},{"id":"openai/azure-gpt-4o","name":"Azure gpt-4o","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-05-13","url":"https://llmpricing.dev/m/openai/azure-gpt-4o/"},{"id":"zhipuai/glm-z1-airx","name":"GLM Z1 AirX","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/zhipuai/glm-z1-airx/"},{"id":"baidu/ernie-5.0-thinking-preview","name":"Ernie 5.0 Thinking Preview","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":1,"output":3.5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":3.5,"cacheRead":0.5},"blendedRef":1.625,"blendedMin":1.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":22.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-18","lastUpdated":"2025-11-18","url":"https://llmpricing.dev/m/baidu/ernie-5.0-thinking-preview/"},{"id":"cohere/command-a-reasoning-08-2025","name":"Cohere Command A (08/2025)","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/cohere/command-a-reasoning-08-2025/"},{"id":"inception/mercury-2","name":"Mercury 2","lab":"inception","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":50000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"inception","input":0.25,"output":0.75,"cacheRead":0.025,"official":true},"cheapest":{"provider":"nano-gpt","input":0.25,"output":0.75,"cacheRead":0.025},"blendedRef":0.375,"blendedMin":0.375,"blendedTrusted":0.375,"spread":1.3,"hostCount":5,"pricedHostCount":5,"aa":{"idx":21.9,"coding":31.1,"agentic":9.5,"speed":835,"ttft":3.93,"taskCost":0.0798},"usage":null,"releaseDate":"2026-02-24","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/inception/mercury-2/"},{"id":"misc/fastgpt","name":"Web Answer","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":7.5,"output":7.5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":7.5,"output":7.5,"cacheRead":null},"blendedRef":7.5,"blendedMin":7.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/fastgpt/"},{"id":"deepseek/deepseek-chat-2","name":"DeepSeek V3/Deepseek Chat","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.425,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.425,"cacheRead":0.05},"blendedRef":0.1813,"blendedMin":0.1813,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2026-02-28","url":"https://llmpricing.dev/m/deepseek/deepseek-chat-2/"},{"id":"misc/auto-model-basic","name":"Auto model (Basic)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":9.996,"output":19.992,"cacheRead":4.998,"official":false},"cheapest":{"provider":"nano-gpt","input":9.996,"output":19.992,"cacheRead":4.998},"blendedRef":12.495,"blendedMin":12.495,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/misc/auto-model-basic/"},{"id":"misc/baichuan4-turbo","name":"Baichuan 4 Turbo","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.42,"output":2.42,"cacheRead":1.21,"official":false},"cheapest":{"provider":"nano-gpt","input":2.42,"output":2.42,"cacheRead":1.21},"blendedRef":2.42,"blendedMin":2.42,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-19","lastUpdated":"2025-08-19","url":"https://llmpricing.dev/m/misc/baichuan4-turbo/"},{"id":"anthropic/claude-opus-4-1-thinking-1024","name":"Claude 4.1 Opus Thinking (1K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-thinking-1024/"},{"id":"misc/yi-medium-200k","name":"Yi Medium 200k","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.499,"output":2.499,"cacheRead":1.2495,"official":false},"cheapest":{"provider":"nano-gpt","input":2.499,"output":2.499,"cacheRead":1.2495},"blendedRef":2.499,"blendedMin":2.499,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-03-01","url":"https://llmpricing.dev/m/misc/yi-medium-200k/"},{"id":"anthropic/claude-sonnet-4-thinking","name":"Claude 4 Sonnet Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-thinking/"},{"id":"misc/deepclaude","name":"DeepClaude","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-10","lastUpdated":"2025-02-01","url":"https://llmpricing.dev/m/misc/deepclaude/"},{"id":"zhipuai/glm-4-air","name":"GLM-4 Air","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003},"blendedRef":0.2006,"blendedMin":0.2006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-06-05","url":"https://llmpricing.dev/m/zhipuai/glm-4-air/"},{"id":"google/gemini-2.0-pro-reasoner","name":"Gemini 2.0 Pro Reasoner","lab":"google","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"nano-gpt","input":1.292,"output":4.998,"cacheRead":0.323,"official":false},"cheapest":{"provider":"nano-gpt","input":1.292,"output":4.998,"cacheRead":0.323},"blendedRef":2.2185,"blendedMin":2.2185,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-02-05","url":"https://llmpricing.dev/m/google/gemini-2.0-pro-reasoner/"},{"id":"anthropic/claude-opus-4-5-20251101-thinking","name":"Claude 4.5 Opus Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2025-11-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-20251101-thinking/"},{"id":"alibaba/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":245800,"contextRange":[240000,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":1.32,"output":7.9,"cacheRead":0.132,"official":true},"cheapest":{"provider":"openrouter","input":1.027,"output":6.162,"cacheRead":null},"blendedRef":2.965,"blendedMin":2.3107,"blendedTrusted":2.925,"spread":2.1,"hostCount":13,"pricedHostCount":13,"aa":{"idx":41.1,"coding":null,"agentic":null,"speed":62,"ttft":4.19,"taskCost":null},"usage":null,"releaseDate":"2026-04-20","lastUpdated":"2026-04-20","url":"https://llmpricing.dev/m/alibaba/qwen3.6-max-preview/"},{"id":"alibaba/qwen3.5-27b-bluestar-v3-derestricted","name":"Qwen3.5 27B BlueStar v3 Derestricted","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/alibaba/qwen3.5-27b-bluestar-v3-derestricted/"},{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[256000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"alibaba-cn","input":1.77744,"output":5.33231,"cacheRead":0.22218,"official":true},"cheapest":{"provider":"deepinfra","input":1.65,"output":4.951,"cacheRead":0.206},"blendedRef":2.6662,"blendedMin":2.4753,"blendedTrusted":2.4753,"spread":1.5,"hostCount":22,"pricedHostCount":19,"aa":{"idx":58.1,"coding":71.8,"agentic":58.4,"speed":45,"ttft":2.63,"taskCost":1.132},"usage":{"rank":41,"tokens":695047056016,"share":0.002604728636916176},"releaseDate":"2026-08-03","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/alibaba/qwen3.8-max/"},{"id":"google/gemini-2.5-pro-preview-06-05","name":"Gemini 2.5 Pro Preview 0605","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":[1048576,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":0.25,"official":false},"cheapest":{"provider":"jiekou","input":1.125,"output":9,"cacheRead":null},"blendedRef":4.375,"blendedMin":3.0938,"blendedTrusted":null,"spread":2.2,"hostCount":3,"pricedHostCount":3,"aa":{"idx":23.4,"coding":46.7,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-06-05","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-preview-06-05/"},{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[198000,1000000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":3,"output":15,"cacheRead":0.3,"official":true},"cheapest":{"provider":"qihang-ai","input":0.43,"output":2.14,"cacheRead":null},"blendedRef":6,"blendedMin":0.8575,"blendedTrusted":6,"spread":8.7,"hostCount":18,"pricedHostCount":18,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-20250929/"},{"id":"sarvam/sarvam-105b","name":"Sarvam 105B","lab":"sarvam","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":{"provider":"fastrouter","input":0.04,"output":0.16,"cacheRead":null},"blendedRef":null,"blendedMin":0.07,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":2,"aa":{"idx":11.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/sarvam/sarvam-105b/"},{"id":"openai/azure-gpt-4-turbo","name":"Azure gpt-4-turbo","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":10,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":10,"output":30,"cacheRead":null},"blendedRef":15,"blendedMin":15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/openai/azure-gpt-4-turbo/"},{"id":"misc/auto-model-premium","name":"Auto model (Premium)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":9.996,"output":19.992,"cacheRead":4.998,"official":false},"cheapest":{"provider":"nano-gpt","input":9.996,"output":19.992,"cacheRead":4.998},"blendedRef":12.495,"blendedMin":12.495,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/misc/auto-model-premium/"},{"id":"deepseek/deepseek-r1-sambanova","name":"DeepSeek R1 Fast","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":4.998,"output":6.987,"cacheRead":2.499,"official":false},"cheapest":{"provider":"nano-gpt","input":4.998,"output":6.987,"cacheRead":2.499},"blendedRef":5.4953,"blendedMin":5.4953,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-20","lastUpdated":"2025-02-20","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-sambanova/"},{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[262144,1048576],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"alibaba-cn","input":0.5,"output":3,"cacheRead":0.05,"official":true},"cheapest":{"provider":"requesty","input":0.28,"output":1.12,"cacheRead":0.028},"blendedRef":1.125,"blendedMin":0.49,"blendedTrusted":0.7,"spread":4.3,"hostCount":28,"pricedHostCount":23,"aa":{"idx":39.4,"coding":55.9,"agentic":20.7,"speed":57,"ttft":2.23,"taskCost":0.2424},"usage":{"rank":66,"tokens":44650639999,"share":0.00016733082984147317},"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/alibaba/qwen3.7-plus/"},{"id":"alibaba/qwen3.7-max-thinking","name":"Qwen3.7 Max Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.5,"output":7.5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":7.5,"cacheRead":0.5},"blendedRef":3.75,"blendedMin":3.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-21","lastUpdated":"2026-05-21","url":"https://llmpricing.dev/m/alibaba/qwen3.7-max-thinking/"},{"id":"anthropic/claude-opus-4-1-thinking-32000","name":"Claude 4.1 Opus Thinking (32K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-thinking-32000/"},{"id":"misc/jamba-large","name":"Jamba Large","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.989,"output":7.99,"cacheRead":0.9945,"official":false},"cheapest":{"provider":"nano-gpt","input":1.989,"output":7.99,"cacheRead":0.9945},"blendedRef":3.4893,"blendedMin":3.4893,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/misc/jamba-large/"},{"id":"anthropic/claude-sonnet-4-thinking-64000","name":"Claude 4 Sonnet Thinking (64K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-thinking-64000/"},{"id":"anthropic/claude-opus-4-thinking","name":"Claude 4 Opus Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-thinking/"},{"id":"alibaba/qwen3.7-flash","name":"Qwen3.7 Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[991000,1000000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"alibaba-cn","input":0.02962,"output":0.1185,"cacheRead":0.002962,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.02962,"output":0.1185,"cacheRead":0.002962},"blendedRef":0.0518,"blendedMin":0.0518,"blendedTrusted":0.0518,"spread":6.8,"hostCount":9,"pricedHostCount":9,"aa":null,"usage":{"rank":52,"tokens":340780962696,"share":0.0012770961689098945},"releaseDate":"2026-07-15","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/alibaba/qwen3.7-flash/"},{"id":"alibaba/qwen3.5-27b-queen-derestricted","name":"Qwen3.5 27B Queen Derestricted","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/alibaba/qwen3.5-27b-queen-derestricted/"},{"id":"misc/doubao-seed-2-0-code-preview-260215","name":"Doubao Seed 2.0 Code Preview","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.782,"output":3.893,"cacheRead":0.391,"official":false},"cheapest":{"provider":"aihubmix","input":0.48,"output":2.41,"cacheRead":0.09644},"blendedRef":1.5598,"blendedMin":0.9625,"blendedTrusted":null,"spread":1.6,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/misc/doubao-seed-2-0-code-preview-260215/"},{"id":"misc/exa-answer","name":"Exa (Answer)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.5,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":2.5,"cacheRead":null},"blendedRef":2.5,"blendedMin":2.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-06-04","url":"https://llmpricing.dev/m/misc/exa-answer/"},{"id":"baidu/ernie-5.1","name":"ERNIE 5.1","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":119000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.75,"output":3,"cacheRead":0.75,"official":false},"cheapest":{"provider":"nano-gpt","input":0.75,"output":3,"cacheRead":0.75},"blendedRef":1.3125,"blendedMin":1.3125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-10","lastUpdated":"2026-05-10","url":"https://llmpricing.dev/m/baidu/ernie-5.1/"},{"id":"stepfun/step-r1-v-mini","name":"Step R1 V Mini","lab":"stepfun","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.5,"output":11,"cacheRead":1.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":11,"cacheRead":1.25},"blendedRef":4.625,"blendedMin":4.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-04-08","url":"https://llmpricing.dev/m/stepfun/step-r1-v-mini/"},{"id":"openai/azure-gpt-4o-mini","name":"Azure gpt-4o-mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.075,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/azure-gpt-4o-mini/"},{"id":"moonshotai/kimi-k2-instruct-fast","name":"Kimi K2 0711 Fast","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2025-07-15","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-instruct-fast/"},{"id":"misc/hermes-high","name":"Hermes High","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":2.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":2.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/misc/hermes-high/"},{"id":"alibaba/qwen3.7-plus-thinking","name":"Qwen3.7 Plus Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":983616,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.4,"output":1.6,"cacheRead":0.08,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.6,"cacheRead":0.08},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/alibaba/qwen3.7-plus-thinking/"},{"id":"deepseek/deepseek-chat-cheaper","name":"DeepSeek V3/Chat Cheaper","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.425,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.425,"cacheRead":0.05},"blendedRef":0.1813,"blendedMin":0.1813,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/deepseek/deepseek-chat-cheaper/"},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity Reasoning Pro","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":127000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2,"output":8,"cacheRead":1,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":8,"cacheRead":1},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-reasoning-pro/"},{"id":"misc/auto-model-standard","name":"Auto model (Standard)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":9.996,"output":19.992,"cacheRead":4.998,"official":false},"cheapest":{"provider":"nano-gpt","input":9.996,"output":19.992,"cacheRead":4.998},"blendedRef":12.495,"blendedMin":12.495,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/misc/auto-model-standard/"},{"id":"google/gemini-2.0-pro-exp-02-05","name":"Gemini 2.0 Pro 0205","lab":"google","kind":"text","status":"ga","openWeights":false,"context":2097152,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":1.989,"output":7.956,"cacheRead":0.49725,"official":false},"cheapest":{"provider":"nano-gpt","input":1.989,"output":7.956,"cacheRead":0.49725},"blendedRef":3.4808,"blendedMin":3.4808,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-05","lastUpdated":"2025-02-05","url":"https://llmpricing.dev/m/google/gemini-2.0-pro-exp-02-05/"},{"id":"alibaba/qwen3.8-27b-thinking","name":"Qwen3.8 27B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.2,"output":1.4,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":1.4,"cacheRead":0.04},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/alibaba/qwen3.8-27b-thinking/"},{"id":"zhipuai/glm-4-plus","name":"GLM-4 Plus","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":7.497,"output":7.497,"cacheRead":3.7485,"official":false},"cheapest":{"provider":"nano-gpt","input":7.497,"output":7.497,"cacheRead":3.7485},"blendedRef":7.497,"blendedMin":7.497,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-20","lastUpdated":"2024-08-01","url":"https://llmpricing.dev/m/zhipuai/glm-4-plus/"},{"id":"tencent/hunyuan-turbos-20250226","name":"Hunyuan Turbo S","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":24000,"contextRange":[24000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.187,"output":0.374,"cacheRead":0.0935,"official":false},"cheapest":{"provider":"nano-gpt","input":0.187,"output":0.374,"cacheRead":0.0935},"blendedRef":0.2338,"blendedMin":0.2338,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-27","lastUpdated":"2026-03-08","url":"https://llmpricing.dev/m/tencent/hunyuan-turbos-20250226/"},{"id":"baidu/ernie-5.1-thinking","name":"ERNIE 5.1 Thinking","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":119000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.75,"output":3,"cacheRead":0.75,"official":false},"cheapest":{"provider":"nano-gpt","input":0.75,"output":3,"cacheRead":0.75},"blendedRef":1.3125,"blendedMin":1.3125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-10","lastUpdated":"2026-05-10","url":"https://llmpricing.dev/m/baidu/ernie-5.1-thinking/"},{"id":"misc/hermes-low","name":"Hermes Low","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"nano-gpt","input":0.25,"output":1.5,"cacheRead":0.025,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/misc/hermes-low/"},{"id":"cohere/command-a-plus-05-2026","name":"Cohere Command A+ (05/2026)","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-20","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/cohere/command-a-plus-05-2026/"},{"id":"google/gemini-2.5-flash-lite-preview-09-2025-thinking","name":"Gemini 2.5 Flash Lite Preview (09/2025) – Thinking","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.01},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-preview-09-2025-thinking/"},{"id":"misc/holo3-35b-a3b","name":"Holo3-35B-A3B","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.25,"output":1.8,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":1.8,"cacheRead":0.125},"blendedRef":0.6375,"blendedMin":0.6375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/holo3-35b-a3b/"},{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[192000,200000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":1,"output":5,"cacheRead":0.1,"official":true},"cheapest":{"provider":"qihang-ai","input":0.14,"output":0.71,"cacheRead":null},"blendedRef":2,"blendedMin":0.2825,"blendedTrusted":2,"spread":8.6,"hostCount":21,"pricedHostCount":21,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-20251001/"},{"id":"misc/claw-medium","name":"Claw Medium","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.315,"output":1.26,"cacheRead":0.1575,"official":false},"cheapest":{"provider":"nano-gpt","input":0.315,"output":1.26,"cacheRead":0.1575},"blendedRef":0.5513,"blendedMin":0.5513,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/misc/claw-medium/"},{"id":"google/gemma-4-e2b-it","name":"Gemma 4 E2B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nano-gpt","input":0.02,"output":0.1,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.02,"output":0.1,"cacheRead":0.01},"blendedRef":0.04,"blendedMin":0.04,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-e2b-it/"},{"id":"misc/hermes-medium","name":"Hermes Medium","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.315,"output":1.26,"cacheRead":0.1575,"official":false},"cheapest":{"provider":"nano-gpt","input":0.315,"output":1.26,"cacheRead":0.1575},"blendedRef":0.5513,"blendedMin":0.5513,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/misc/hermes-medium/"},{"id":"perplexity/sonar-pro","name":"Perplexity Pro","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":1.5},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-pro/"},{"id":"alibaba/qwen3.7-flash-thinking","name":"Qwen3.7 Flash Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":983616,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.03,"output":0.13,"cacheRead":0.006,"official":false},"cheapest":{"provider":"nano-gpt","input":0.03,"output":0.13,"cacheRead":0.006},"blendedRef":0.055,"blendedMin":0.055,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-15","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/alibaba/qwen3.7-flash-thinking/"},{"id":"anthropic/claude-opus-4-1-thinking-8192","name":"Claude 4.1 Opus Thinking (8K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-thinking-8192/"},{"id":"mistral/mistral-code-agent-latest","name":"Mistral Code Agent Latest","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":2,"cacheRead":0.2},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/mistral/mistral-code-agent-latest/"},{"id":"anthropic/claude-opus-4-thinking-1024","name":"Claude 4 Opus Thinking (1K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-thinking-1024/"},{"id":"misc/baichuan-m2","name":"Baichuan M2 32B Medical","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":15.73,"output":15.73,"cacheRead":7.865,"official":false},"cheapest":{"provider":"nano-gpt","input":15.73,"output":15.73,"cacheRead":7.865},"blendedRef":15.73,"blendedMin":15.73,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-19","lastUpdated":"2025-08-19","url":"https://llmpricing.dev/m/misc/baichuan-m2/"},{"id":"google/gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash 0520 Thinking","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.15,"output":3.5,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":3.5,"cacheRead":0.015},"blendedRef":0.9875,"blendedMin":0.9875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-05-20-thinking/"},{"id":"alibaba/qvq-max","name":"Qwen: QvQ Max","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":1.2,"output":4.8,"cacheRead":0.6,"official":false},"cheapest":{"provider":"nano-gpt","input":1.2,"output":4.8,"cacheRead":0.6},"blendedRef":2.1,"blendedMin":2.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-28","lastUpdated":"2025-03-28","url":"https://llmpricing.dev/m/alibaba/qvq-max/"},{"id":"meituan/longcat-2.0","name":"LongCat-2.0","lab":"meituan","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048756],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"longcat","input":0.75,"output":2.95,"cacheRead":0.015,"official":true},"cheapest":{"provider":"openrouter","input":0.3,"output":1.2,"cacheRead":0.006},"blendedRef":1.3,"blendedMin":0.525,"blendedTrusted":1.3,"spread":2.5,"hostCount":3,"pricedHostCount":3,"aa":{"idx":34,"coding":45.3,"agentic":22,"speed":39,"ttft":2.62,"taskCost":0.1213},"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/meituan/longcat-2.0/"},{"id":"anthropic/gemma-4-31b-claude-4.6-opus-reasoning-distilled","name":"Gemma 4 31B Claude 4.6 Opus Reasoning Distilled","lab":"anthropic","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.0306,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.0306},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/anthropic/gemma-4-31b-claude-4.6-opus-reasoning-distilled/"},{"id":"google/gemma-4-31b-cognitive-unshackled","name":"Gemma 4 31B Cognitive Unshackled","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/google/gemma-4-31b-cognitive-unshackled/"},{"id":"alibaba/qwen-long","name":"Qwen Long 10M","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":10000000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.1003,"output":0.408,"cacheRead":0.05015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1003,"output":0.408,"cacheRead":0.05015},"blendedRef":0.1772,"blendedMin":0.1772,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-01","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-long/"},{"id":"misc/brave-research","name":"Brave (Research)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":5,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":5,"cacheRead":null},"blendedRef":5,"blendedMin":5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-10","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/brave-research/"},{"id":"zhipuai/glm-4-plus-0111","name":"GLM 4 Plus 0111","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":9.996,"output":9.996,"cacheRead":4.998,"official":false},"cheapest":{"provider":"nano-gpt","input":9.996,"output":9.996,"cacheRead":4.998},"blendedRef":9.996,"blendedMin":9.996,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-19","lastUpdated":"2025-02-19","url":"https://llmpricing.dev/m/zhipuai/glm-4-plus-0111/"},{"id":"mistral/mistral-code-latest","name":"Mistral Code Latest","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.9,"cacheRead":0.15},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/mistral/mistral-code-latest/"},{"id":"alibaba/qwen3.5-flash-thinking","name":"Qwen3.5 Flash Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":991808,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.05},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-flash-thinking/"},{"id":"zhipuai/glm-4-flash","name":"GLM-4 Flash","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1003,"output":0.1003,"cacheRead":0.05015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1003,"output":0.1003,"cacheRead":0.05015},"blendedRef":0.1003,"blendedMin":0.1003,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-08-01","url":"https://llmpricing.dev/m/zhipuai/glm-4-flash/"},{"id":"alibaba/qwen3.5-27b-thinking","name":"Qwen3.5 27B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":260096,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.27,"output":2.16,"cacheRead":0.135,"official":false},"cheapest":{"provider":"nano-gpt","input":0.27,"output":2.16,"cacheRead":0.135},"blendedRef":0.7425,"blendedMin":0.7425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-27b-thinking/"},{"id":"anthropic/claude-sonnet-4-thinking-8192","name":"Claude 4 Sonnet Thinking (8K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-thinking-8192/"},{"id":"openai/nano-gpt-help","name":"NanoGPT Help","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":6000,"contextRange":null,"outputLimit":512,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-06","lastUpdated":"2026-06-06","url":"https://llmpricing.dev/m/openai/nano-gpt-help/"},{"id":"misc/jamba-mini-1.6","name":"Jamba Mini 1.6","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1989,"output":0.408,"cacheRead":0.09945,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1989,"output":0.408,"cacheRead":0.09945},"blendedRef":0.2512,"blendedMin":0.2512,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-03-01","url":"https://llmpricing.dev/m/misc/jamba-mini-1.6/"},{"id":"anthropic/claude-opus-4-thinking-8192","name":"Claude 4 Opus Thinking (8K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-thinking-8192/"},{"id":"misc/asi1-mini","name":"ASI1 Mini","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":1,"output":1,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":1,"cacheRead":0.5},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-25","lastUpdated":"2025-03-25","url":"https://llmpricing.dev/m/misc/asi1-mini/"},{"id":"misc/qwen25-vl-72b-instruct","name":"Qwen25 VL 72b","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.69989,"output":0.69989,"cacheRead":0.349945,"official":false},"cheapest":{"provider":"nano-gpt","input":0.69989,"output":0.69989,"cacheRead":0.349945},"blendedRef":0.6999,"blendedMin":0.6999,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-10","lastUpdated":"2025-05-10","url":"https://llmpricing.dev/m/misc/qwen25-vl-72b-instruct/"},{"id":"anthropic/claude-sonnet-4-20250514","name":"Claude 4 Sonnet","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":29.8,"coding":37.6,"agentic":17.6,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-20250514/"},{"id":"anthropic/claude-sonnet-4-thinking-32768","name":"Claude 4 Sonnet Thinking (32K)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-thinking-32768/"},{"id":"alibaba/qwen3.5-omni-plus","name":"Qwen3.5 Omni Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":983616,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nano-gpt","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":31.3,"coding":null,"agentic":null,"speed":49,"ttft":2.51,"taskCost":null},"usage":null,"releaseDate":"2026-03-30","lastUpdated":"2026-03-30","url":"https://llmpricing.dev/m/alibaba/qwen3.5-omni-plus/"},{"id":"misc/qwen3-max-2026-01-23","name":"Qwen3 Max 2026-01-23","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.2002,"output":6.001,"cacheRead":0.6001,"official":false},"cheapest":{"provider":"nano-gpt","input":1.2002,"output":6.001,"cacheRead":0.6001},"blendedRef":2.4004,"blendedMin":2.4004,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-26","lastUpdated":"2026-01-26","url":"https://llmpricing.dev/m/misc/qwen3-max-2026-01-23/"},{"id":"misc/claw-high","name":"Claw High","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":2.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":2.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/misc/claw-high/"},{"id":"baidu/ernie-x1.1-preview","name":"ERNIE X1.1","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":64000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.075,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-10","lastUpdated":"2025-09-10","url":"https://llmpricing.dev/m/baidu/ernie-x1.1-preview/"},{"id":"misc/yi-large","name":"Yi Large","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":3.196,"output":3.196,"cacheRead":1.598,"official":false},"cheapest":{"provider":"nano-gpt","input":3.196,"output":3.196,"cacheRead":1.598},"blendedRef":3.196,"blendedMin":3.196,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-05-13","url":"https://llmpricing.dev/m/misc/yi-large/"},{"id":"google/gemini-2.5-flash-nothinking","name":"Gemini 2.5 Flash (No Thinking)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"nano-gpt","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-05","lastUpdated":"2025-06-05","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-nothinking/"},{"id":"google/gemini-2.5-flash-preview-04-17","name":"Gemini 2.5 Flash Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.015},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":24.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-04-17","lastUpdated":"2025-04-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-04-17/"},{"id":"zhipuai/glm-4.6-derestricted-v5","name":"GLM 4.6 Derestricted v5","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":1.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.5,"cacheRead":0.2},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-derestricted-v5/"},{"id":"zhipuai/glm-4","name":"GLM-4","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":14.994,"output":14.994,"cacheRead":7.497,"official":false},"cheapest":{"provider":"nano-gpt","input":14.994,"output":14.994,"cacheRead":7.497},"blendedRef":14.994,"blendedMin":14.994,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-16","url":"https://llmpricing.dev/m/zhipuai/glm-4/"},{"id":"google/gemma-4-e4b-it","name":"Gemma 4 E4B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nano-gpt","input":0.04,"output":0.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"nano-gpt","input":0.04,"output":0.2,"cacheRead":0.02},"blendedRef":0.08,"blendedMin":0.08,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-e4b-it/"},{"id":"misc/universal-summarizer","name":"Universal Summarizer","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":30,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":30,"output":30,"cacheRead":null},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/universal-summarizer/"},{"id":"alibaba/qwen3.5-122b-a10b-thinking","name":"Qwen3.5 122B A10B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.437,"output":3.496,"cacheRead":0.103788,"official":false},"cheapest":{"provider":"nano-gpt","input":0.437,"output":3.496,"cacheRead":0.103788},"blendedRef":1.2018,"blendedMin":1.2018,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-122b-a10b-thinking/"},{"id":"anthropic/claude-haiku-4-5-20251001-thinking","name":"Claude Haiku 4.5 Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-20251001-thinking/"},{"id":"misc/pokee-isaac","name":"Pokee-Isaac 28B","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":10000000,"contextRange":null,"outputLimit":60000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.15,"output":1,"cacheRead":0.075,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":1,"cacheRead":0.075},"blendedRef":0.3625,"blendedMin":0.3625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-04","lastUpdated":"2026-08-04","url":"https://llmpricing.dev/m/misc/pokee-isaac/"},{"id":"misc/brave","name":"Brave (Answers)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":5,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":5,"cacheRead":null},"blendedRef":5,"blendedMin":5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-13","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/brave/"},{"id":"sarvam/sarvam-30b","name":"Sarvam 30B","lab":"sarvam","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":[65536,128000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":{"provider":"fastrouter","input":0.02,"output":0.1,"cacheRead":null},"blendedRef":null,"blendedMin":0.04,"blendedTrusted":null,"spread":1.4,"hostCount":3,"pricedHostCount":2,"aa":{"idx":6.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-02-18","lastUpdated":"2026-02-18","url":"https://llmpricing.dev/m/sarvam/sarvam-30b/"},{"id":"google/gemma-4-31b-darkidol","name":"Gemma 4 31B DarkIdol","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.306,"cacheRead":0.153},"blendedRef":0.306,"blendedMin":0.306,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/google/gemma-4-31b-darkidol/"},{"id":"alibaba/qwen3.5-35b-a3b-thinking","name":"Qwen3.5 35B A3B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":260096,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.225,"output":1.8,"cacheRead":0.1125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.225,"output":1.8,"cacheRead":0.1125},"blendedRef":0.6188,"blendedMin":0.6188,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-35b-a3b-thinking/"},{"id":"alibaba/cogito-v1-preview-qwen-32b","name":"Cogito v1 Preview Qwen 32B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.8,"output":1.8,"cacheRead":0.9,"official":false},"cheapest":{"provider":"nano-gpt","input":1.8,"output":1.8,"cacheRead":0.9},"blendedRef":1.8,"blendedMin":1.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-10","lastUpdated":"2025-05-10","url":"https://llmpricing.dev/m/alibaba/cogito-v1-preview-qwen-32b/"},{"id":"tencent/hunyuan-mt-7b","name":"Hunyuan MT 7B","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":10,"output":20,"cacheRead":5,"official":false},"cheapest":{"provider":"nano-gpt","input":10,"output":20,"cacheRead":5},"blendedRef":12.5,"blendedMin":12.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-15","lastUpdated":"2025-09-18","url":"https://llmpricing.dev/m/tencent/hunyuan-mt-7b/"},{"id":"tencent/hy3","name":"Tencent Hy3","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.066,"output":0.26,"cacheRead":0.029,"official":false},"cheapest":{"provider":"nano-gpt","input":0.066,"output":0.26,"cacheRead":0.029},"blendedRef":0.1145,"blendedMin":0.1145,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3/"},{"id":"mistral/ms3.2-24b-magnum-diamond","name":"MS3.2 24B Magnum Diamond","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-11-24","url":"https://llmpricing.dev/m/mistral/ms3.2-24b-magnum-diamond/"},{"id":"minimax/minimax-m1-80k","name":"MiniMax M1 80K","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.6052,"output":2.4225,"cacheRead":0.3026,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6052,"output":2.4225,"cacheRead":0.3026},"blendedRef":1.0595,"blendedMin":1.0595,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":17.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-08","lastUpdated":"2025-06-16","url":"https://llmpricing.dev/m/minimax/minimax-m1-80k/"},{"id":"meta/l3.1-70b-celeste-v0.1-bf16","name":"Llama 3.1 70B Celeste v0.1","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/l3.1-70b-celeste-v0.1-bf16/"},{"id":"meta/wayfarer-large-70b-llama-3.3","name":"Llama 3.3 70B Wayfarer","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-20","lastUpdated":"2025-02-20","url":"https://llmpricing.dev/m/meta/wayfarer-large-70b-llama-3.3/"},{"id":"nanogpt/coding-router-low","name":"Coding Router Low","lab":"nanogpt","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.028,"official":false},"cheapest":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/nanogpt/coding-router-low/"},{"id":"nanogpt/coding-router-high","name":"Coding Router High","lab":"nanogpt","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":2.2,"cacheRead":0.11},"blendedRef":1.375,"blendedMin":1.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/nanogpt/coding-router-high/"},{"id":"nanogpt/coding-router","name":"Coding Router","lab":"nanogpt","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":2.2,"cacheRead":0.11},"blendedRef":1.375,"blendedMin":1.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/nanogpt/coding-router/"},{"id":"nanogpt/coding-router-medium","name":"Coding Router Medium","lab":"nanogpt","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.028,"official":false},"cheapest":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/nanogpt/coding-router-medium/"},{"id":"nanogpt/coding-router-max","name":"Coding Router Max","lab":"nanogpt","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/nanogpt/coding-router-max/"},{"id":"meta/ms3.2-the-omega-directive-24b-unslop-v2.0","name":"Omega Directive 24B Unslop v2.0","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/meta/ms3.2-the-omega-directive-24b-unslop-v2.0/"},{"id":"nvidia/nemotron-3-nano-30b-a3b-2","name":"Nvidia Nemotron 3 Nano 30B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[128000,256000],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.17,"output":0.68,"cacheRead":0.085,"official":false},"cheapest":{"provider":"venice","input":0.075,"output":0.3,"cacheRead":null},"blendedRef":0.2975,"blendedMin":0.1312,"blendedTrusted":null,"spread":2.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-30b-a3b-2/"},{"id":"nvidia/llama-3.1-nemotron-70b-instruct-hf","name":"Nvidia Nemotron 70b","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.357,"output":0.408,"cacheRead":0.1785,"official":false},"cheapest":{"provider":"nano-gpt","input":0.357,"output":0.408,"cacheRead":0.1785},"blendedRef":0.3697,"blendedMin":0.3697,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-70b-instruct-hf/"},{"id":"nvidia/nemotron-3-super-120b-a12b-2","name":"Nvidia Nemotron 3 Super 120B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.05,"output":0.25,"cacheRead":0.025,"official":false},"cheapest":{"provider":"nano-gpt","input":0.05,"output":0.25,"cacheRead":0.025},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b-2/"},{"id":"nvidia/nemotron-3-super-120b-a12b-thinking","name":"Nvidia Nemotron 3 Super 120B Thinking","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.05,"output":0.25,"cacheRead":0.025,"official":false},"cheapest":{"provider":"nano-gpt","input":0.05,"output":0.25,"cacheRead":0.025},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b-thinking/"},{"id":"nvidia/nemotron-3-ultra-550b-a55b-thinking","name":"Nvidia Nemotron 3 Ultra 550B Thinking","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-a55b-thinking/"},{"id":"nvidia/nemotron-3.5-lightning-2","name":"Nvidia Nemotron 3.5 Lightning","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.05,"output":0.2,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.05,"output":0.2,"cacheRead":0.01},"blendedRef":0.0875,"blendedMin":0.0875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-lightning-2/"},{"id":"nvidia/nemotron-3-ultra-550b-a55b-2","name":"Nvidia Nemotron 3 Ultra 550B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-a55b-2/"},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1-2","name":"Nvidia Nemotron Super 49B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.15,"cacheRead":0.075,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.15,"cacheRead":0.075},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-08","lastUpdated":"2025-08-08","url":"https://llmpricing.dev/m/nvidia/llama-3.3-nemotron-super-49b-v1-2/"},{"id":"nvidia/nemotron-3.5-lightning-thinking","name":"Nvidia Nemotron 3.5 Lightning Thinking","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.05,"output":0.2,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.05,"output":0.2,"cacheRead":0.01},"blendedRef":0.0875,"blendedMin":0.0875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-lightning-thinking/"},{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion 3.0","lab":"aion-labs","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":3,"output":6,"cacheRead":0.75,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":6,"cacheRead":0.75},"blendedRef":3.75,"blendedMin":3.75,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-07","lastUpdated":"2026-07-07","url":"https://llmpricing.dev/m/aion-labs/aion-3.0/"},{"id":"meta/aion-rp-llama-3.1-8b","name":"Llama 3.1 8b (uncensored)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.8,"output":1.6,"cacheRead":0.4,"official":false},"cheapest":{"provider":"nano-gpt","input":0.8,"output":1.6,"cacheRead":0.4},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/aion-rp-llama-3.1-8b/"},{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","lab":"aion-labs","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.8,"output":1.6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.8,"output":1.6,"cacheRead":0.2},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/aion-labs/aion-2.0/"},{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion 3.0 Mini","lab":"aion-labs","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.7,"output":1.4,"cacheRead":0.18,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":1.4,"cacheRead":0.18},"blendedRef":0.875,"blendedMin":0.875,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-07","lastUpdated":"2026-07-07","url":"https://llmpricing.dev/m/aion-labs/aion-3.0-mini/"},{"id":"meta/remm-slerp-l2-13b","name":"ReMM SLERP 13B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":6144,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.799,"output":1.207,"cacheRead":0.3995,"official":false},"cheapest":{"provider":"openrouter","input":0.45,"output":0.65,"cacheRead":null},"blendedRef":0.901,"blendedMin":0.5,"blendedTrusted":null,"spread":1.8,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2023-07-22","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/meta/remm-slerp-l2-13b/"},{"id":"openai/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":65535,"contextRange":[65535,65536],"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":0.62,"output":0.62,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.62,"blendedMin":0.493,"blendedTrusted":null,"spread":1.3,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-04-16","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/openai/wizardlm-2-8x22b/"},{"id":"zhipuai/glm-4.5v","name":"GLM-4.5V","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":64000,"contextRange":[64000,128000],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zai","input":0.6,"output":1.8,"cacheRead":null,"official":true},"cheapest":{"provider":"302ai","input":0.29,"output":0.86,"cacheRead":null},"blendedRef":0.9,"blendedMin":0.4325,"blendedTrusted":0.9,"spread":2.1,"hostCount":12,"pricedHostCount":12,"aa":{"idx":9,"coding":null,"agentic":null,"speed":83,"ttft":1.77,"taskCost":null},"usage":null,"releaseDate":"2025-08-11","lastUpdated":"2025-08-11","url":"https://llmpricing.dev/m/zhipuai/glm-4.5v/"},{"id":"zhipuai/glm-4.6-thinking","name":"GLM 4.6 Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.35,"output":1.4,"cacheRead":0.175,"official":false},"cheapest":{"provider":"nano-gpt","input":0.35,"output":1.4,"cacheRead":0.175},"blendedRef":0.6125,"blendedMin":0.6125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-thinking/"},{"id":"zhipuai/glm-4.5v-thinking","name":"GLM 4.5V Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":64000,"contextRange":null,"outputLimit":96000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.6,"output":1.8,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6,"output":1.8,"cacheRead":0.3},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-11","lastUpdated":"2025-08-11","url":"https://llmpricing.dev/m/zhipuai/glm-4.5v-thinking/"},{"id":"zhipuai/glm-5v-turbo-thinking","name":"GLM 5V Turbo Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":202800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":1.2,"output":4,"cacheRead":0.24,"official":false},"cheapest":{"provider":"nano-gpt","input":1.2,"output":4,"cacheRead":0.24},"blendedRef":1.9,"blendedMin":1.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-04-01","url":"https://llmpricing.dev/m/zhipuai/glm-5v-turbo-thinking/"},{"id":"deepseek/deepseek-v4-flash-thinking","name":"DeepSeek V4 Flash (Thinking)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.0028,"official":false},"cheapest":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-thinking/"},{"id":"deepseek/deepseek-v4-pro-thinking","name":"DeepSeek V4 Pro (Thinking)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":2.2,"cacheRead":0.11},"blendedRef":1.375,"blendedMin":1.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-thinking/"},{"id":"deepseek/deepseek-v3.2-thinking","name":"DeepSeek V3.2 Thinking","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,163000],"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"vercel","input":0.62,"output":1.85,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.28,"output":0.42,"cacheRead":0.14},"blendedRef":0.9275,"blendedMin":0.315,"blendedTrusted":0.9275,"spread":2.2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-thinking/"},{"id":"deepseek/deepseek-prover-v2-671b","name":"DeepSeek Prover v2 671B","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":160000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":2.5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"novita-ai","input":0.7,"output":2.5,"cacheRead":null},"blendedRef":1.375,"blendedMin":1.15,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-15","lastUpdated":"2025-04-30","url":"https://llmpricing.dev/m/deepseek/deepseek-prover-v2-671b/"},{"id":"deepseek/deepseek-latest","name":"DeepSeek Latest","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":2.5,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":2.5,"cacheRead":0.04},"blendedRef":1.45,"blendedMin":1.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-03","lastUpdated":"2026-05-03","url":"https://llmpricing.dev/m/deepseek/deepseek-latest/"},{"id":"deepseek/deepseek-v4-flash-0731-thinking","name":"DeepSeek V4 Flash 0731 (Thinking)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.014,"official":false},"cheapest":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.014},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-31","lastUpdated":"2026-07-31","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-0731-thinking/"},{"id":"deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","lab":"deepseek","kind":"text","status":"beta","openWeights":true,"context":1048576,"contextRange":[262144,1310720],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"arcee","input":0.14,"output":0.28,"cacheRead":0.028,"official":false},"cheapest":{"provider":"openrouter","input":0.065,"output":0.14,"cacheRead":0.014},"blendedRef":0.175,"blendedMin":0.0838,"blendedTrusted":null,"spread":2.2,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-08-01","lastUpdated":"2026-08-02","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-latest/"},{"id":"deepseek/deepseek-v4-pro-0813-thinking","name":"DeepSeek V4 Pro 0813 Thinking","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":2.5,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":2.5,"cacheRead":0.04},"blendedRef":1.45,"blendedMin":1.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-0813-thinking/"},{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","lab":"arcee-ai","kind":"text","status":"beta","openWeights":true,"context":262100,"contextRange":[262100,262144],"outputLimit":80000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.25,"output":0.8999999999999999,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.22,"output":0.85,"cacheRead":0.06},"blendedRef":0.4125,"blendedMin":0.3775,"blendedTrusted":0.4125,"spread":1.1,"hostCount":5,"pricedHostCount":5,"aa":{"idx":18.7,"coding":25.8,"agentic":3.7,"speed":197,"ttft":1.38,"taskCost":0.164},"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/arcee-ai/trinity-large-thinking/"},{"id":"google/gemma-4-26b-a4b-it-thinking","name":"Gemma 4 26B A4B Thinking","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.13,"output":0.4,"cacheRead":0.065,"official":false},"cheapest":{"provider":"nano-gpt","input":0.13,"output":0.4,"cacheRead":0.065},"blendedRef":0.1975,"blendedMin":0.1975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-it-thinking/"},{"id":"google/gemma-4-26b-a4b-it-2","name":"Gemma 4 26B A4B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"novita-ai","input":0.13,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"empiriolabs","input":0.05,"output":0.29,"cacheRead":0.025},"blendedRef":0.1975,"blendedMin":0.11,"blendedTrusted":null,"spread":2.6,"hostCount":4,"pricedHostCount":4,"aa":{"idx":26.1,"coding":39.3,"agentic":11,"speed":null,"ttft":null,"taskCost":0.0391},"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-it-2/"},{"id":"google/gemini-3.1-pro-preview-low","name":"Gemini 3.1 Pro (Preview Low)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-21","lastUpdated":"2026-02-21","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-low/"},{"id":"google/gemini-3.5-flash-thinking","name":"Gemini 3.5 Flash Thinking","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":1.5,"output":9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":1.5,"output":9,"cacheRead":0.15},"blendedRef":3.375,"blendedMin":3.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-thinking/"},{"id":"google/gemini-3-flash-preview-thinking","name":"Gemini 3 Flash Thinking","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":3,"cacheRead":0.05},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-17","lastUpdated":"2025-12-17","url":"https://llmpricing.dev/m/google/gemini-3-flash-preview-thinking/"},{"id":"google/gemini-pro-latest","name":"Gemini Pro Latest","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1048576,1048756],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"llmgateway","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-29","lastUpdated":"2026-03-29","url":"https://llmpricing.dev/m/google/gemini-pro-latest/"},{"id":"google/gemma-4-31b-it-thinking","name":"Gemma 4 31B Thinking","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.35,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.35,"cacheRead":0.05},"blendedRef":0.1625,"blendedMin":0.1625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-thinking/"},{"id":"google/gemini-3.1-pro-preview-high","name":"Gemini 3.1 Pro (Preview High)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-21","lastUpdated":"2026-02-21","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-high/"},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":{"provider":"meta","input":1.25,"output":4.25,"cacheRead":0.15,"official":true},"cheapest":{"provider":"nano-gpt","input":1.25,"output":4.25,"cacheRead":0.15},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":1,"hostCount":10,"pricedHostCount":10,"aa":{"idx":56.8,"coding":72.2,"agentic":49.3,"speed":null,"ttft":null,"taskCost":0.3992},"usage":null,"releaseDate":"2026-08-05","lastUpdated":"2026-08-05","url":"https://llmpricing.dev/m/meta/muse-spark-1.2/"},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048576],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","video","audio"],"reference":{"provider":"meta","input":1.25,"output":4.25,"cacheRead":0.15,"official":true},"cheapest":{"provider":"nano-gpt","input":1.25,"output":4.25,"cacheRead":0.15},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":1,"hostCount":10,"pricedHostCount":10,"aa":{"idx":53.2,"coding":71.3,"agentic":39.7,"speed":200,"ttft":1.48,"taskCost":0.2923},"usage":{"rank":70,"tokens":22575848852,"share":0.00008460428613935732},"releaseDate":"2026-04-08","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/meta/muse-spark-1.1/"},{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor (Data Used for Training)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.002,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.002},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-05","lastUpdated":"2026-08-05","url":"https://llmpricing.dev/m/meta/muse-spark-1.2-contributor/"},{"id":"meta/veiled-calla-12b","name":"Veiled Calla 12B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-13","lastUpdated":"2025-04-13","url":"https://llmpricing.dev/m/meta/veiled-calla-12b/"},{"id":"google/amoral-gemma3-27b-v2","name":"Amoral Gemma3 27B v2","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-23","lastUpdated":"2025-05-23","url":"https://llmpricing.dev/m/google/amoral-gemma3-27b-v2/"},{"id":"alibaba/grayline-qwen3-8b","name":"Grayline Qwen3 8B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.3,"cacheRead":0.15},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/alibaba/grayline-qwen3-8b/"},{"id":"poolside/laguna-s-2.1-thinking","name":"Laguna S 2.1 Thinking","lab":"poolside","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.01},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/poolside/laguna-s-2.1-thinking/"},{"id":"poolside/laguna-m.1","name":"Laguna M.1","lab":"poolside","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[32768,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"poolside","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.4,"cacheRead":0.1},"blendedRef":0,"blendedMin":0.25,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":1,"aa":null,"usage":{"rank":71,"tokens":21131045263,"share":0.00007918980196822958},"releaseDate":"2026-04-28","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/poolside/laguna-m.1/"},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","lab":"poolside","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"poolside","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":{"provider":"openrouter","input":0.09,"output":0.18,"cacheRead":0.009},"blendedRef":0,"blendedMin":0.1125,"blendedTrusted":0.125,"spread":1.1,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/poolside/laguna-s-2.1/"},{"id":"xai/grok-4.20","name":"Grok 4.20","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":[1000000,2000000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":1,"official":false},"cheapest":{"provider":"openrouter","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":3,"blendedMin":1.5625,"blendedTrusted":null,"spread":1.6,"hostCount":4,"pricedHostCount":4,"aa":{"idx":38,"coding":null,"agentic":null,"speed":99,"ttft":22.33,"taskCost":null},"usage":null,"releaseDate":"2026-03-31","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/xai/grok-4.20/"},{"id":"xai/grok-4.6","name":"Grok 4.6","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":null,"outputLimit":500000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"xai","input":2,"output":6,"cacheRead":0.5,"official":true},"cheapest":{"provider":"merge-gateway","input":1.5,"output":4.5,"cacheRead":0.375},"blendedRef":3,"blendedMin":2.25,"blendedTrusted":3,"spread":1.5,"hostCount":18,"pricedHostCount":18,"aa":{"idx":60.9,"coding":76.8,"agentic":58.7,"speed":56,"ttft":36.89,"taskCost":0.8367},"usage":{"rank":46,"tokens":572643336667,"share":0.002146013690505337},"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/xai/grok-4.6/"},{"id":"xai/grok-4.5","name":"Grok 4.5","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":[500000,1000000],"outputLimit":500000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"xai","input":2,"output":6,"cacheRead":0.3,"official":true},"cheapest":{"provider":"requesty","input":1.8,"output":5.4,"cacheRead":0.45},"blendedRef":3,"blendedMin":2.7,"blendedTrusted":3,"spread":1.3,"hostCount":22,"pricedHostCount":21,"aa":{"idx":55.8,"coding":72.4,"agentic":48.9,"speed":50,"ttft":14.03,"taskCost":0.3601},"usage":{"rank":30,"tokens":1385258114170,"share":0.005191334094962393},"releaseDate":"2026-07-08","lastUpdated":"2026-07-08","url":"https://llmpricing.dev/m/xai/grok-4.5/"},{"id":"xai/grok-latest","name":"Grok Latest","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openrouter","input":2,"output":6,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":0.5},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-05-03","lastUpdated":"2026-07-08","url":"https://llmpricing.dev/m/xai/grok-latest/"},{"id":"xai/grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[128000,2000000],"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"xai","input":1.25,"output":2.5,"cacheRead":0.2,"official":true},"cheapest":{"provider":"openrouter","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":1.5625,"spread":1.6,"hostCount":6,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2026-03-31","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/xai/grok-4.20-multi-agent/"},{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"xai","input":1,"output":2,"cacheRead":0.2,"official":true},"cheapest":{"provider":"requesty","input":0.9,"output":1.8,"cacheRead":0.09},"blendedRef":1.25,"blendedMin":1.125,"blendedTrusted":1.25,"spread":1.1,"hostCount":17,"pricedHostCount":16,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/xai/grok-build-0.1/"},{"id":"perceptron/perceptron-mk1","name":"Perceptron Mk1","lab":"perceptron","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"openrouter","input":0.15,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":1.5,"cacheRead":0.075},"blendedRef":0.4875,"blendedMin":0.4875,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/perceptron/perceptron-mk1/"},{"id":"bytedance-seed/seed-2.0-code","name":"ByteDance Seed 2.0 Code","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.5,"output":3,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":3,"cacheRead":0.25},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.0-code/"},{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed 2.0 Lite","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.25,"output":2,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":2,"cacheRead":0.125},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.0-lite/"},{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed 2.1 Turbo","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/bytedance-seed/seed-2-1-turbo/"},{"id":"moonshotai/kimi-latest","name":"Kimi Latest","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[256000,1048576],"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":2.5,"output":13.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"privatemode-ai","input":1.791,"output":8.9436,"cacheRead":0.1733},"blendedRef":5.25,"blendedMin":3.5792,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-05-03","lastUpdated":"2026-05-03","url":"https://llmpricing.dev/m/moonshotai/kimi-latest/"},{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32768,256000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"huggingface","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2},"blendedRef":1.5,"blendedMin":0.75,"blendedTrusted":0.7675,"spread":2.6,"hostCount":6,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2025-07-11","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-instruct/"},{"id":"moonshotai/kimi-k2.5-thinking","name":"Kimi K2.5 Thinking","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.9,"cacheRead":0.15},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-thinking/"},{"id":"moonshotai/kimi-k2.6-thinking","name":"Kimi K2.6 Thinking","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.6,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":2.6,"cacheRead":0.125},"blendedRef":1.025,"blendedMin":1.025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-thinking/"},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"moonshotai","input":1.9,"output":8,"cacheRead":0.38,"official":true},"cheapest":{"provider":"aihubmix","input":1.9,"output":7.999,"cacheRead":0.32167},"blendedRef":3.425,"blendedMin":3.4247,"blendedTrusted":3.425,"spread":1,"hostCount":10,"pricedHostCount":10,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-highspeed/"},{"id":"moonshotai/kimi-k2-0711-preview","name":"Kimi K2 0711","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"moonshotai","input":0.6,"output":2.5,"cacheRead":0.15,"official":true},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2},"blendedRef":1.075,"blendedMin":0.75,"blendedTrusted":1.075,"spread":1.5,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2025-07-14","lastUpdated":"2025-07-14","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-0711-preview/"},{"id":"featherless-ai/qwerky-72b","name":"Qwerky 72B","lab":"featherless-ai","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/featherless-ai/qwerky-72b/"},{"id":"thedrummer/unslopnemo-12b-v4.1","name":"UnslopNemo 12b v4","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/thedrummer/unslopnemo-12b-v4.1/"},{"id":"thedrummer/anubis-70b-v1.1","name":"Anubis 70B v1.1","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.31,"output":0.31,"cacheRead":0.155,"official":false},"cheapest":{"provider":"nano-gpt","input":0.31,"output":0.31,"cacheRead":0.155},"blendedRef":0.31,"blendedMin":0.31,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/thedrummer/anubis-70b-v1.1/"},{"id":"thedrummer/anubis-70b-v1","name":"Anubis 70B v1","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.31,"output":0.31,"cacheRead":0.155,"official":false},"cheapest":{"provider":"nano-gpt","input":0.31,"output":0.31,"cacheRead":0.155},"blendedRef":0.31,"blendedMin":0.31,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/thedrummer/anubis-70b-v1/"},{"id":"thedrummer/cydonia-24b-v4.3","name":"The Drummer Cydonia 24B v4.3","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.12,"output":0.15,"cacheRead":0.06,"official":false},"cheapest":{"provider":"nano-gpt","input":0.12,"output":0.15,"cacheRead":0.06},"blendedRef":0.1275,"blendedMin":0.1275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-25","lastUpdated":"2025-12-25","url":"https://llmpricing.dev/m/thedrummer/cydonia-24b-v4.3/"},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer Skyfall 36B V2","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[32000,32768],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":0.55,"output":0.8,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.55,"output":0.8,"cacheRead":0.25},"blendedRef":0.6125,"blendedMin":0.6125,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-03-10","lastUpdated":"2025-03-10","url":"https://llmpricing.dev/m/thedrummer/skyfall-36b-v2/"},{"id":"thedrummer/rocinante-12b-v1.1","name":"Rocinante 12b","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":[16384,65536],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.408,"output":0.595,"cacheRead":0.204,"official":false},"cheapest":{"provider":"openrouter","input":0.25,"output":0.5,"cacheRead":null},"blendedRef":0.4548,"blendedMin":0.3125,"blendedTrusted":null,"spread":1.6,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-09-30","url":"https://llmpricing.dev/m/thedrummer/rocinante-12b-v1.1/"},{"id":"thedrummer/cydonia-24b-v2","name":"The Drummer Cydonia 24B v2","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1003,"output":0.1207,"cacheRead":0.05015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1003,"output":0.1207,"cacheRead":0.05015},"blendedRef":0.1054,"blendedMin":0.1054,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-17","lastUpdated":"2025-02-17","url":"https://llmpricing.dev/m/thedrummer/cydonia-24b-v2/"},{"id":"thedrummer/cydonia-24b-v4.1","name":"The Drummer Cydonia 24B v4.1","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.35,"output":0.55,"cacheRead":0.16,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":0.5,"cacheRead":0.15},"blendedRef":0.4,"blendedMin":0.35,"blendedTrusted":null,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-08-19","lastUpdated":"2025-09-27","url":"https://llmpricing.dev/m/thedrummer/cydonia-24b-v4.1/"},{"id":"thedrummer/cydonia-24b-v4","name":"The Drummer Cydonia 24B v4","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.2414,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.2414,"cacheRead":0.1003},"blendedRef":0.2108,"blendedMin":0.2108,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-22","lastUpdated":"2025-07-22","url":"https://llmpricing.dev/m/thedrummer/cydonia-24b-v4/"},{"id":"thedrummer/magidonia-24b-v4.3","name":"The Drummer Magidonia 24B v4.3","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1003,"output":0.1207,"cacheRead":0.05015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1003,"output":0.1207,"cacheRead":0.05015},"blendedRef":0.1054,"blendedMin":0.1054,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-25","lastUpdated":"2025-12-25","url":"https://llmpricing.dev/m/thedrummer/magidonia-24b-v4.3/"},{"id":"anthropic/claude-opus-4.6-thinking","name":"Claude 4.6 Opus Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.6-thinking/"},{"id":"anthropic/claude-opus-4.8-thinking","name":"Claude Opus 4.8 Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.8-thinking/"},{"id":"anthropic/claude-opus-4.6-thinking-low","name":"Claude 4.6 Opus Thinking Low","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.6-thinking-low/"},{"id":"anthropic/claude-opus-4.7","name":"Claude 4.7 Opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.7/"},{"id":"anthropic/claude-opus-4.7-thinking","name":"Claude 4.7 Opus Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.7-thinking/"},{"id":"anthropic/claude-haiku-latest","name":"Claude Haiku Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-29","lastUpdated":"2026-03-29","url":"https://llmpricing.dev/m/anthropic/claude-haiku-latest/"},{"id":"anthropic/claude-opus-latest","name":"Claude Opus Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openrouter","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-29","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/anthropic/claude-opus-latest/"},{"id":"anthropic/claude-opus-4.6-thinking-max","name":"Claude 4.6 Opus Thinking Max","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.6-thinking-max/"},{"id":"anthropic/claude-sonnet-latest","name":"Claude Sonnet Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-latest/"},{"id":"anthropic/claude-opus-4.6","name":"Claude 4.6 Opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.6/"},{"id":"anthropic/claude-sonnet-4.6-thinking","name":"Claude Sonnet 4.6 Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"aihubmix","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4.6-thinking/"},{"id":"anthropic/claude-fable-latest","name":"Claude Fable Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openrouter","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"nano-gpt","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/claude-fable-latest/"},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","lab":"anthropic","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":10,"output":50,"cacheRead":1,"official":true},"cheapest":{"provider":"xpersona","input":3,"output":18.5,"cacheRead":0.3},"blendedRef":20,"blendedMin":6.875,"blendedTrusted":20,"spread":4,"hostCount":31,"pricedHostCount":28,"aa":{"idx":62.1,"coding":76.5,"agentic":56.6,"speed":67,"ttft":148.12,"taskCost":3.1396},"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/claude-fable-5/"},{"id":"anthropic/claude-sonnet-5-thinking","name":"Claude Sonnet 5 Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-5-thinking/"},{"id":"anthropic/claude-opus-4.6-thinking-medium","name":"Claude 4.6 Opus Thinking Medium","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.6-thinking-medium/"},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.856,"output":14.246,"cacheRead":1.428,"official":false},"cheapest":{"provider":"nano-gpt","input":2.856,"output":14.246,"cacheRead":1.428},"blendedRef":5.7035,"blendedMin":5.7035,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-30","lastUpdated":"2024-08-30","url":"https://llmpricing.dev/m/cohere/command-r-plus-08-2024/"},{"id":"cohere/north-mini-code","name":"Cohere North Mini Code 1.0","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/cohere/north-mini-code/"},{"id":"meta/eva-llama-3.33-70b-v0.1","name":"EVA-LLaMA-3.33-70B-v0.1","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.006,"output":2.006,"cacheRead":1.003,"official":false},"cheapest":{"provider":"nano-gpt","input":2.006,"output":2.006,"cacheRead":1.003},"blendedRef":2.006,"blendedMin":2.006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/meta/eva-llama-3.33-70b-v0.1/"},{"id":"alibaba/eva-qwen2.5-32b-v0.2","name":"EVA-Qwen2.5-32B-v0.2","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.799,"output":0.799,"cacheRead":0.3995,"official":false},"cheapest":{"provider":"nano-gpt","input":0.799,"output":0.799,"cacheRead":0.3995},"blendedRef":0.799,"blendedMin":0.799,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/alibaba/eva-qwen2.5-32b-v0.2/"},{"id":"alibaba/eva-qwen2.5-72b-v0.2","name":"EVA-Qwen2.5-72B-v0.2","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.799,"output":0.799,"cacheRead":0.3995,"official":false},"cheapest":{"provider":"nano-gpt","input":0.799,"output":0.799,"cacheRead":0.3995},"blendedRef":0.799,"blendedMin":0.799,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2025-09-25","url":"https://llmpricing.dev/m/alibaba/eva-qwen2.5-72b-v0.2/"},{"id":"meta/eva-llama-3.33-70b-v0.0","name":"EVA Llama 3.33 70B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.006,"output":2.006,"cacheRead":1.003,"official":false},"cheapest":{"provider":"nano-gpt","input":2.006,"output":2.006,"cacheRead":1.003},"blendedRef":2.006,"blendedMin":2.006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/meta/eva-llama-3.33-70b-v0.0/"},{"id":"bytedance/doubao-seed-2.1-pro","name":"Doubao Seed 2.1 Pro","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":5,"cacheRead":0.5},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/bytedance/doubao-seed-2.1-pro/"},{"id":"bytedance/doubao-seed-character","name":"Doubao Seed Character","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.1179,"output":0.2947,"cacheRead":0.0236,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1179,"output":0.2947,"cacheRead":0.0236},"blendedRef":0.1621,"blendedMin":0.1621,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-18","lastUpdated":"2026-07-18","url":"https://llmpricing.dev/m/bytedance/doubao-seed-character/"},{"id":"bytedance/doubao-seed-2.1-turbo","name":"Doubao Seed 2.1 Turbo","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/bytedance/doubao-seed-2.1-turbo/"},{"id":"moonshotai/k2-think","name":"K2-Think","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.17,"output":0.68,"cacheRead":0.085,"official":false},"cheapest":{"provider":"nano-gpt","input":0.17,"output":0.68,"cacheRead":0.085},"blendedRef":0.2975,"blendedMin":0.2975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/moonshotai/k2-think/"},{"id":"alibaba/deepseek-r1-distill-qwen-32b-abliterated","name":"DeepSeek R1 Qwen Abliterated","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.4,"output":1.4,"cacheRead":0.7,"official":false},"cheapest":{"provider":"nano-gpt","input":1.4,"output":1.4,"cacheRead":0.7},"blendedRef":1.4,"blendedMin":1.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-01-20","url":"https://llmpricing.dev/m/alibaba/deepseek-r1-distill-qwen-32b-abliterated/"},{"id":"alibaba/qwen2.5-32b-instruct-abliterated","name":"Qwen 2.5 32B Abliterated","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-06","lastUpdated":"2025-01-06","url":"https://llmpricing.dev/m/alibaba/qwen2.5-32b-instruct-abliterated/"},{"id":"meta/llama-3.3-70b-instruct-abliterated","name":"Llama 3.3 70B Instruct abliterated","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-08","lastUpdated":"2025-08-08","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct-abliterated/"},{"id":"deepseek/deepseek-r1-distill-llama-70b-abliterated","name":"DeepSeek R1 Llama 70B Abliterated","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-01-20","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-distill-llama-70b-abliterated/"},{"id":"meta/llama-xlam-2-70b-fc-r","name":"Llama-xLAM-2 70B fc-r","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.5,"output":2.5,"cacheRead":1.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":2.5,"cacheRead":1.25},"blendedRef":2.5,"blendedMin":2.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-13","lastUpdated":"2025-04-13","url":"https://llmpricing.dev/m/meta/llama-xlam-2-70b-fc-r/"},{"id":"openai/o3-mini-low","name":"OpenAI o3-mini (Low)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-31","lastUpdated":"2025-01-31","url":"https://llmpricing.dev/m/openai/o3-mini-low/"},{"id":"openai/o1-pro","name":"OpenAI o1 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":150,"output":600,"cacheRead":75,"official":false},"cheapest":{"provider":"nano-gpt","input":150,"output":600,"cacheRead":75},"blendedRef":262.5,"blendedMin":262.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-19","lastUpdated":"2025-03-19","url":"https://llmpricing.dev/m/openai/o1-pro/"},{"id":"openai/gpt-4-turbo-preview","name":"GPT-4 Turbo Preview","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":10,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":10,"output":30,"cacheRead":null},"blendedRef":15,"blendedMin":15,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/gpt-4-turbo-preview/"},{"id":"openai/o3-deep-research","name":"OpenAI o3 Deep Research","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":11,"output":44,"cacheRead":5.5,"official":false},"cheapest":{"provider":"nano-gpt","input":11,"output":44,"cacheRead":5.5},"blendedRef":19.25,"blendedMin":19.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-26","lastUpdated":"2024-06-26","url":"https://llmpricing.dev/m/openai/o3-deep-research/"},{"id":"openai/o4-mini-high","name":"OpenAI o4-mini high","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":1.1,"output":4.4,"cacheRead":0.275,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-04","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-high/"},{"id":"openai/gpt-5.6-luna-pro","name":"GPT-5.6 Luna Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"venice","input":1.25,"output":7.5,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.6,"cacheRead":0.01},"blendedRef":2.8125,"blendedMin":0.225,"blendedTrusted":null,"spread":12.5,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna-pro/"},{"id":"openai/o1","name":"OpenAI o1","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":15,"output":60,"cacheRead":7.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":60,"cacheRead":7.5},"blendedRef":26.25,"blendedMin":26.25,"blendedTrusted":26.25,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-12-05","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/o1/"},{"id":"openai/o3","name":"OpenAI o3","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":8,"cacheRead":1},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o3/"},{"id":"openai/gpt-chat-latest","name":"GPT Chat Latest","lab":"openai","kind":"text","status":"beta","openWeights":false,"context":128000,"contextRange":[128000,1050000],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"azure","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":11.25,"blendedMin":5.625,"blendedTrusted":11.25,"spread":2,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-05-05","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/openai/gpt-chat-latest/"},{"id":"openai/o4-mini-deep-research","name":"OpenAI o4-mini Deep Research","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.2,"output":8.8,"cacheRead":1.1,"official":false},"cheapest":{"provider":"nano-gpt","input":2.2,"output":8.8,"cacheRead":1.1},"blendedRef":3.85,"blendedMin":3.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-26","lastUpdated":"2024-06-26","url":"https://llmpricing.dev/m/openai/o4-mini-deep-research/"},{"id":"openai/gpt-4o-search-preview","name":"GPT-4o Search Preview","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-10","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/gpt-4o-search-preview/"},{"id":"openai/o3-mini-high","name":"OpenAI o3-mini (High)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-02-12","url":"https://llmpricing.dev/m/openai/o3-mini-high/"},{"id":"openai/gpt-5.1-2025-11-13","name":"GPT-5.1 (2025-11-13)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-2025-11-13/"},{"id":"openai/gpt-latest","name":"GPT Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"nano-gpt","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-29","lastUpdated":"2026-03-29","url":"https://llmpricing.dev/m/openai/gpt-latest/"},{"id":"openai/o3-pro-2025-06-10","name":"OpenAI o3-pro (2025-06-10)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":22,"output":88,"cacheRead":11,"official":false},"cheapest":{"provider":"nano-gpt","input":22,"output":88,"cacheRead":11},"blendedRef":38.5,"blendedMin":38.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-06-10","url":"https://llmpricing.dev/m/openai/o3-pro-2025-06-10/"},{"id":"openai/gpt-5.6-terra-pro","name":"GPT-5.6 Terra Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"venice","input":3.125,"output":18.75,"cacheRead":0.3125,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":6,"cacheRead":0.1},"blendedRef":7.0313,"blendedMin":2.25,"blendedTrusted":null,"spread":3.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra-pro/"},{"id":"openai/o4-mini","name":"OpenAI o4-mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.1,"output":4.4,"cacheRead":0.275,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini/"},{"id":"openai/o3-mini","name":"OpenAI o3-mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"nano-gpt","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":1.925,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-12-20","lastUpdated":"2025-01-29","url":"https://llmpricing.dev/m/openai/o3-mini/"},{"id":"openai/gpt-5.6-sol-pro","name":"GPT-5.6 Sol Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"venice","input":6.25,"output":37.5,"cacheRead":0.625,"official":false},"cheapest":{"provider":"nano-gpt","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":14.0625,"blendedMin":5.625,"blendedTrusted":null,"spread":2.5,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-pro/"},{"id":"openai/gpt-4o-mini-search-preview","name":"GPT-4o mini Search Preview","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-03-10","lastUpdated":"2025-01","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-search-preview/"},{"id":"openai/o1-preview","name":"OpenAI o1-preview","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":15,"output":60,"cacheRead":7.5,"official":false},"cheapest":{"provider":"nano-gpt","input":15,"output":60,"cacheRead":7.5},"blendedRef":26.25,"blendedMin":26.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":17.2,"coding":34,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-09-12","url":"https://llmpricing.dev/m/openai/o1-preview/"},{"id":"openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","lab":"openai","kind":"classify","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.075,"output":0.3,"cacheRead":0.037,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.07,"output":0.2,"cacheRead":null},"blendedRef":0.1312,"blendedMin":0.1025,"blendedTrusted":0.1025,"spread":1.1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-10-29","lastUpdated":"2025-10-29","url":"https://llmpricing.dev/m/openai/gpt-oss-safeguard-20b/"},{"id":"alibaba/qwenlong-l1-32b","name":"QwenLong L1 32B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":40960,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.14,"output":0.6,"cacheRead":0.07,"official":false},"cheapest":{"provider":"nano-gpt","input":0.14,"output":0.6,"cacheRead":0.07},"blendedRef":0.255,"blendedMin":0.255,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwenlong-l1-32b/"},{"id":"meta/l3.3-ms-evayale-70b","name":"Evayale 70b ","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/l3.3-ms-evayale-70b/"},{"id":"meta/l3.3-nevoria-r1-70b","name":"Steelskull Nevoria R1 70b","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/l3.3-nevoria-r1-70b/"},{"id":"meta/l3.3-ms-nevoria-70b","name":"Steelskull Nevoria 70b","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/l3.3-ms-nevoria-70b/"},{"id":"meta/l3.3-electra-r1-70b","name":"Steelskull Electra R1 70b","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.69989,"output":0.69989,"cacheRead":0.349945,"official":false},"cheapest":{"provider":"nano-gpt","input":0.69989,"output":0.69989,"cacheRead":0.349945},"blendedRef":0.6999,"blendedMin":0.6999,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/l3.3-electra-r1-70b/"},{"id":"meta/l3.3-cu-mai-r1-70b","name":"Llama 3.3 70B Cu Mai","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/l3.3-cu-mai-r1-70b/"},{"id":"deepseek/deepseek-v3.1-terminus-thinking-2","name":"DeepSeek V3.1 Terminus (Thinking)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.25,"output":0.7,"cacheRead":0.125,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":0.7,"cacheRead":0.125},"blendedRef":0.3625,"blendedMin":0.3625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-22","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus-thinking-2/"},{"id":"deepseek/deepseek-v3.2-exp-thinking-2","name":"DeepSeek V3.2 Exp Thinking","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.28,"output":0.42,"cacheRead":0.14,"official":false},"cheapest":{"provider":"nano-gpt","input":0.28,"output":0.42,"cacheRead":0.14},"blendedRef":0.315,"blendedMin":0.315,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-exp-thinking-2/"},{"id":"deepseek/deepseek-v3.1-terminus-2","name":"DeepSeek V3.1 Terminus","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,163840],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abacus","input":0.27,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.25,"output":0.7,"cacheRead":0.125},"blendedRef":0.4525,"blendedMin":0.3625,"blendedTrusted":0.4525,"spread":1.1,"hostCount":6,"pricedHostCount":6,"aa":{"idx":31.4,"coding":43.5,"agentic":19.9,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-22","lastUpdated":"2025-09-22","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus-2/"},{"id":"deepseek/deepseek-v3.1-thinking","name":"DeepSeek V3.1 Thinking","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.7,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.7,"cacheRead":0.1},"blendedRef":0.325,"blendedMin":0.325,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-thinking/"},{"id":"stepfun/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"stepfun-ai","input":0.1,"output":0.3,"cacheRead":0.02,"official":true},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.3,"cacheRead":0.05},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1,"hostCount":6,"pricedHostCount":4,"aa":{"idx":26.5,"coding":null,"agentic":null,"speed":214,"ttft":1.14,"taskCost":null},"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/stepfun/step-3.5-flash-2603/"},{"id":"mistral/nemomix-unleashed-12b","name":"NemoMix 12B Unleashed","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/nemomix-unleashed-12b/"},{"id":"openai/dmind-1-mini","name":"DMind-1-Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.4,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.4,"cacheRead":0.1},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-06-01","url":"https://llmpricing.dev/m/openai/dmind-1-mini/"},{"id":"deepreinforce/ornith-1.5-35b-a3b","name":"Ornith 1.5 35B","lab":"deepreinforce","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.01},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/deepreinforce/ornith-1.5-35b-a3b/"},{"id":"deepreinforce/ornith-1.5-35b-a3b-thinking","name":"Ornith 1.5 35B Thinking","lab":"deepreinforce","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.01},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/deepreinforce/ornith-1.5-35b-a3b-thinking/"},{"id":"meta/shisa-v2.1-llama3.3-70b","name":"Shisa V2.1 Llama 3.3 70B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/shisa-v2.1-llama3.3-70b/"},{"id":"meta/shisa-v2-llama3.3-70b","name":"Shisa V2 Llama 3.3 70B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":0.5,"cacheRead":0.25},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/meta/shisa-v2-llama3.3-70b/"},{"id":"nousresearch/hermes-4-70b-thinking","name":"Hermes 4 (Thinking)","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.3995,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.3995,"cacheRead":0.1003},"blendedRef":0.2503,"blendedMin":0.2503,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-17","lastUpdated":"2025-09-17","url":"https://llmpricing.dev/m/nousresearch/hermes-4-70b-thinking/"},{"id":"nousresearch/hermes-4-405b-thinking","name":"Hermes 4 Large (Thinking)","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.15},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/nousresearch/hermes-4-405b-thinking/"},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Hermes 3 70B","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.408,"output":0.408,"cacheRead":0.204,"official":false},"cheapest":{"provider":"nano-gpt","input":0.408,"output":0.408,"cacheRead":0.204},"blendedRef":0.408,"blendedMin":0.408,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":4.8,"coding":null,"agentic":null,"speed":34,"ttft":1.97,"taskCost":null},"usage":null,"releaseDate":"2026-01-07","lastUpdated":"2026-01-07","url":"https://llmpricing.dev/m/nousresearch/hermes-3-llama-3.1-70b/"},{"id":"nousresearch/hermes-4-70b-2","name":"Hermes 4 Medium","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.3995,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.3995,"cacheRead":0.1003},"blendedRef":0.2503,"blendedMin":0.2503,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-03","lastUpdated":"2025-07-03","url":"https://llmpricing.dev/m/nousresearch/hermes-4-70b-2/"},{"id":"nousresearch/hermes-4-405b-2","name":"Hermes 4 Large","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.15},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/nousresearch/hermes-4-405b-2/"},{"id":"stepfun/step-3.7-flash-thinking","name":"Step 3.7 Flash Thinking","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.2,"output":1.15,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":1.15,"cacheRead":0.04},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/stepfun/step-3.7-flash-thinking/"},{"id":"meta/l3.3-70b-euryale-v2.3","name":"Llama 3.3 70B Euryale","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":20480,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/l3.3-70b-euryale-v2.3/"},{"id":"meta/l3.1-70b-hanami-x1","name":"Llama 3.1 70B Hanami","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/l3.1-70b-hanami-x1/"},{"id":"meta/l3.1-70b-euryale-v2.2","name":"Llama 3.1 70B Euryale","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":20480,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.306,"output":0.357,"cacheRead":0.153,"official":false},"cheapest":{"provider":"nano-gpt","input":0.306,"output":0.357,"cacheRead":0.153},"blendedRef":0.3188,"blendedMin":0.3188,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/l3.1-70b-euryale-v2.2/"},{"id":"meta/l3-8b-stheno-v3.2","name":"Sao10K Stheno 8b","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003},"blendedRef":0.2006,"blendedMin":0.2006,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-11-29","url":"https://llmpricing.dev/m/meta/l3-8b-stheno-v3.2/"},{"id":"meta/meta-llama-3-70b-instruct-abliterated-v3.5","name":"Llama 3 70B abliterated","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/meta/meta-llama-3-70b-instruct-abliterated-v3.5/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507-2","name":"Qwen 3 235b A22B 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[131000,262144],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":0.22,"output":0.88,"cacheRead":null,"official":false},"cheapest":{"provider":"tensorx","input":0.072,"output":0.464,"cacheRead":0.018},"blendedRef":0.385,"blendedMin":0.17,"blendedTrusted":0.385,"spread":3.1,"hostCount":3,"pricedHostCount":3,"aa":{"idx":19.9,"coding":22.1,"agentic":3.8,"speed":64,"ttft":2.69,"taskCost":0.0637},"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-09-18","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507-2/"},{"id":"alibaba/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,262144],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"edenai","input":0.4,"output":1.6,"cacheRead":null,"official":false},"cheapest":{"provider":"deepinfra","input":0.2,"output":0.88,"cacheRead":0.11},"blendedRef":0.7,"blendedMin":0.37,"blendedTrusted":0.37,"spread":2,"hostCount":13,"pricedHostCount":13,"aa":{"idx":14.4,"coding":null,"agentic":null,"speed":47,"ttft":2.7,"taskCost":null},"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-instruct/"},{"id":"alibaba/qwen3.5-397b-a17b-thinking","name":"Qwen3.5 397B A17B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":258048,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.6,"output":3.6,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6,"output":3.6,"cacheRead":0.3},"blendedRef":1.35,"blendedMin":1.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-15","lastUpdated":"2026-02-15","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-a17b-thinking/"},{"id":"alibaba/qwen3-coder-flash","name":"Qwen3 Coder Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[128000,1000000],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.574,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.144,"output":0.574,"cacheRead":null},"blendedRef":0.2515,"blendedMin":0.2515,"blendedTrusted":0.2515,"spread":3.5,"hostCount":11,"pricedHostCount":11,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-flash/"},{"id":"alibaba/qwen3-8b","name":"Qwen3 8B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[40960,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.072,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"novita-ai","input":0.035,"output":0.138,"cacheRead":null},"blendedRef":0.1257,"blendedMin":0.0608,"blendedTrusted":0.1257,"spread":13.4,"hostCount":6,"pricedHostCount":6,"aa":{"idx":8.3,"coding":9,"agentic":1.6,"speed":39,"ttft":3.76,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04-29","url":"https://llmpricing.dev/m/alibaba/qwen3-8b/"},{"id":"alibaba/qwen3.5-plus-thinking","name":"Qwen3.5 Plus Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":983616,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.4,"output":2.4,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":2.4,"cacheRead":0.04},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-plus-thinking/"},{"id":"alibaba/qwen3-coder","name":"Qwen 3 Coder 480B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":106000,"contextRange":[106000,262000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"io-net","input":0.22,"output":0.95,"cacheRead":0.11,"official":false},"cheapest":{"provider":"nano-gpt","input":0.13,"output":0.5,"cacheRead":0.065},"blendedRef":0.4025,"blendedMin":0.2225,"blendedTrusted":0.4025,"spread":1.7,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/alibaba/qwen3-coder/"},{"id":"alibaba/qwen2.5-coder-32b-instruct-2","name":"Qwen 2.5 Coder 32b","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[32000,128000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abacus","input":0.79,"output":0.79,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2006,"output":0.2006,"cacheRead":0.1003},"blendedRef":0.79,"blendedMin":0.2006,"blendedTrusted":null,"spread":3.9,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-11-12","lastUpdated":"2024-11-12","url":"https://llmpricing.dev/m/alibaba/qwen2.5-coder-32b-instruct-2/"},{"id":"alibaba/qwen3-14b","name":"Qwen3 14B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[40960,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.574,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.08,"output":0.24,"cacheRead":0.04},"blendedRef":0.2515,"blendedMin":0.12,"blendedTrusted":0.15,"spread":4.4,"hostCount":5,"pricedHostCount":5,"aa":{"idx":10.4,"coding":13.8,"agentic":1.9,"speed":59,"ttft":2.69,"taskCost":null},"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/alibaba/qwen3-14b/"},{"id":"alibaba/qwen3.6-35b-a3b-thinking","name":"Qwen3.6 35B A3B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.112,"output":0.8,"cacheRead":0.056,"official":false},"cheapest":{"provider":"nano-gpt","input":0.112,"output":0.8,"cacheRead":0.056},"blendedRef":0.284,"blendedMin":0.284,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-thinking/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507-3","name":"Qwen 3 235b A22B 2507 Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":0.5,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":0.5,"cacheRead":0.15},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-11","lastUpdated":"2025-09-11","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507-3/"},{"id":"alibaba/qwen-2.5-72b-instruct","name":"Qwen2.5 72B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.357,"output":0.408,"cacheRead":0.1785,"official":false},"cheapest":{"provider":"nano-gpt","input":0.357,"output":0.408,"cacheRead":0.1785},"blendedRef":0.3697,"blendedMin":0.3697,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-03","lastUpdated":"2025-07-03","url":"https://llmpricing.dev/m/alibaba/qwen-2.5-72b-instruct/"},{"id":"liquid/lfm-2.5-2.6b","name":"LFM2.5 2.6B","lab":"liquid","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.05},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/liquid/lfm-2.5-2.6b/"},{"id":"mistral/mn-12b-mag-mell-r1","name":"Mag Mell R1","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/mn-12b-mag-mell-r1/"},{"id":"xiaomi/mimo-v2.5-thinking","name":"MiMo V2.5 Thinking","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.0028,"official":false},"cheapest":{"provider":"nano-gpt","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-thinking/"},{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[262144,1050000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"xiaomi","input":0.14,"output":0.28,"cacheRead":0.0028,"official":true},"cheapest":{"provider":"requesty","input":0.126,"output":0.252,"cacheRead":0.00252},"blendedRef":0.175,"blendedMin":0.1575,"blendedTrusted":0.175,"spread":5.6,"hostCount":23,"pricedHostCount":18,"aa":{"idx":38,"coding":56.8,"agentic":24.4,"speed":56,"ttft":2.78,"taskCost":0.0104},"usage":{"rank":2,"tokens":28590535017517,"share":0.1071446669118284},"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5/"},{"id":"xiaomi/mimo-v2.5-pro-crof","name":"MiMo V2.5 Pro (Crof)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":0.8,"cacheRead":0.003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":0.8,"cacheRead":0.003},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-23","lastUpdated":"2026-07-23","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-pro-crof/"},{"id":"xiaomi/mimo-v2.5-pro-crof-thinking","name":"MiMo V2.5 Pro Thinking (Crof)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":0.8,"cacheRead":0.003,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":0.8,"cacheRead":0.003},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-23","lastUpdated":"2026-07-23","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-pro-crof-thinking/"},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[262144,1050000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","audio"],"reference":{"provider":"xiaomi","input":0.435,"output":0.87,"cacheRead":0.0036,"official":true},"cheapest":{"provider":"requesty","input":0.3915,"output":0.783,"cacheRead":0.00324},"blendedRef":0.5438,"blendedMin":0.4894,"blendedTrusted":0.5438,"spread":5.6,"hostCount":25,"pricedHostCount":20,"aa":{"idx":42.9,"coding":60.2,"agentic":29.5,"speed":59,"ttft":3.18,"taskCost":0.0339},"usage":{"rank":22,"tokens":2344656533399,"share":0.008786734600795714},"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-pro/"},{"id":"xiaomi/mimo-v2.5-pro-thinking","name":"MiMo V2.5 Pro Thinking","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.435,"output":0.87,"cacheRead":0.0036,"official":false},"cheapest":{"provider":"nano-gpt","input":0.435,"output":0.87,"cacheRead":0.0036},"blendedRef":0.5438,"blendedMin":0.5438,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-pro-thinking/"},{"id":"alibaba/qwen3.6-27b-thinking","name":"Qwen3.6 27B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":260096,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.203,"output":2.24,"cacheRead":0.1015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.203,"output":2.24,"cacheRead":0.1015},"blendedRef":0.7123,"blendedMin":0.7123,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/alibaba/qwen3.6-27b-thinking/"},{"id":"alibaba/qwen3.6-flash","name":"Qwen3.6 Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[991000,1000000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.1875,"output":1.125,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.165,"output":0.99,"cacheRead":0.033},"blendedRef":0.4219,"blendedMin":0.3712,"blendedTrusted":0.4219,"spread":6.1,"hostCount":19,"pricedHostCount":17,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/alibaba/qwen3.6-flash/"},{"id":"meta/neuraldaredevil-8b-abliterated","name":"Neural Daredevil 8B abliterated","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.44,"output":0.44,"cacheRead":0.22,"official":false},"cheapest":{"provider":"nano-gpt","input":0.44,"output":0.44,"cacheRead":0.22},"blendedRef":0.44,"blendedMin":0.44,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/meta/neuraldaredevil-8b-abliterated/"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","lab":"sakana","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048576],"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"sakana","input":5,"output":30,"cacheRead":0.5,"official":true},"cheapest":{"provider":"requesty","input":4.5,"output":27,"cacheRead":0.45},"blendedRef":11.25,"blendedMin":10.125,"blendedTrusted":11.25,"spread":1.2,"hostCount":11,"pricedHostCount":11,"aa":null,"usage":null,"releaseDate":"2026-06-15","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/sakana/fugu-ultra/"},{"id":"sakana/fugu-ultra-v1.1","name":"Fugu Ultra v1.1","lab":"sakana","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":5.25,"output":31.5,"cacheRead":0.525,"official":false},"cheapest":{"provider":"empiriolabs","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.8125,"blendedMin":11.25,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/sakana/fugu-ultra-v1.1/"},{"id":"meta/llama-3.05-nt-storybreaker-ministral-70b","name":"Llama 3.05 Storybreaker Ministral 70b","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/meta/llama-3.05-nt-storybreaker-ministral-70b/"},{"id":"nvidia/llama-3.05-nemotron-tenyxchat-storybreaker-70b","name":"Nemotron Tenyxchat Storybreaker 70b","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/nvidia/llama-3.05-nemotron-tenyxchat-storybreaker-70b/"},{"id":"amazon/manta-mini-1.0","name":"Manta Mini 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.02,"output":0.16,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.02,"output":0.16,"cacheRead":0.01},"blendedRef":0.055,"blendedMin":0.055,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-20","lastUpdated":"2025-12-20","url":"https://llmpricing.dev/m/amazon/manta-mini-1.0/"},{"id":"amazon/manta-flash-1.0","name":"Manta Flash 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.02,"output":0.16,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nano-gpt","input":0.02,"output":0.16,"cacheRead":0.01},"blendedRef":0.055,"blendedMin":0.055,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-20","lastUpdated":"2025-12-20","url":"https://llmpricing.dev/m/amazon/manta-flash-1.0/"},{"id":"amazon/manta-pro-1.0","name":"Manta Pro 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.06,"output":0.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.06,"output":0.5,"cacheRead":0.03},"blendedRef":0.17,"blendedMin":0.17,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-20","lastUpdated":"2025-12-20","url":"https://llmpricing.dev/m/amazon/manta-pro-1.0/"},{"id":"meta/dracarys-72b-instruct","name":"Llama 3.1 70B Dracarys 2","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-02","lastUpdated":"2025-08-02","url":"https://llmpricing.dev/m/meta/dracarys-72b-instruct/"},{"id":"mistral/starcannon-unleashed-12b-v1.0","name":"Mistral Nemo Starcannon 12b v1","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/starcannon-unleashed-12b-v1.0/"},{"id":"zhipuai/glm-5.3-thinking","name":"GLM 5.3 Preview Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"nano-gpt","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/zhipuai/glm-5.3-thinking/"},{"id":"zhipuai/glm-5-original-thinking","name":"GLM 5 Original Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":3.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":3.2,"cacheRead":0.2},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-11","lastUpdated":"2026-02-11","url":"https://llmpricing.dev/m/zhipuai/glm-5-original-thinking/"},{"id":"zhipuai/glm-4.7-flash-thinking","name":"GLM 4.7 Flash Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.07,"output":0.4,"cacheRead":0.035,"official":false},"cheapest":{"provider":"nano-gpt","input":0.07,"output":0.4,"cacheRead":0.035},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flash-thinking/"},{"id":"zhipuai/glm-4.5-air-thinking","name":"GLM 4.5 Air (Thinking)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.12,"output":0.8,"cacheRead":0.06,"official":false},"cheapest":{"provider":"nano-gpt","input":0.12,"output":0.8,"cacheRead":0.06},"blendedRef":0.29,"blendedMin":0.29,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-air-thinking/"},{"id":"zhipuai/glm-5.1-thinking","name":"GLM 5.1 Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.75,"output":2.6,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.75,"output":2.6,"cacheRead":0.15},"blendedRef":1.2125,"blendedMin":1.2125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-thinking/"},{"id":"zhipuai/glm-4.6v-original","name":"GLM 4.6V Original","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":24000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.6,"output":0.9,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6,"output":0.9,"cacheRead":0.3},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-original/"},{"id":"zhipuai/glm-4.6-turbo","name":"GLM 4.6 Turbo","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":204800,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":3,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":3,"cacheRead":0.5},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-02","lastUpdated":"2025-10-02","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-turbo/"},{"id":"zhipuai/glm-5-thinking","name":"GLM 5 Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.55,"cacheRead":0.13,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":2.55,"cacheRead":0.13},"blendedRef":1.0125,"blendedMin":1.0125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-thinking/"},{"id":"zhipuai/glm-4.6v-flash","name":"GLM-4.6V-Flash","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"huggingface","input":0.3,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.05},"blendedRef":0.45,"blendedMin":0.175,"blendedTrusted":0.45,"spread":3,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-flash/"},{"id":"zhipuai/glm-4.7-thinking","name":"GLM 4.7 Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-thinking/"},{"id":"zhipuai/glm-4.7-flash-original","name":"GLM 4.7 Flash Original","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.07,"output":0.4,"cacheRead":0.035,"official":false},"cheapest":{"provider":"nano-gpt","input":0.07,"output":0.4,"cacheRead":0.035},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flash-original/"},{"id":"zhipuai/glm-latest","name":"GLM Latest","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"nano-gpt","input":0.42,"output":1.32,"cacheRead":0.078},"blendedRef":2.15,"blendedMin":0.645,"blendedTrusted":null,"spread":3.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-05-03","lastUpdated":"2026-08-19","url":"https://llmpricing.dev/m/zhipuai/glm-latest/"},{"id":"zhipuai/glm-5.3","name":"GLM 5.3 Preview","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"nano-gpt","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/zhipuai/glm-5.3/"},{"id":"zhipuai/glm-4.7-flash-original-thinking","name":"GLM 4.7 Flash Original Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.07,"output":0.4,"cacheRead":0.035,"official":false},"cheapest":{"provider":"nano-gpt","input":0.07,"output":0.4,"cacheRead":0.035},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flash-original-thinking/"},{"id":"zhipuai/glm-4.6v","name":"GLM-4.6V","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,200000],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zai","input":0.3,"output":0.9,"cacheRead":null,"official":true},"cheapest":{"provider":"zenmux","input":0.14,"output":0.42,"cacheRead":0.03},"blendedRef":0.45,"blendedMin":0.21,"blendedTrusted":0.45,"spread":2.1,"hostCount":12,"pricedHostCount":11,"aa":{"idx":16.9,"coding":null,"agentic":null,"speed":70,"ttft":3.5,"taskCost":null},"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v/"},{"id":"zhipuai/glm-4.5-thinking","name":"GLM 4.5 (Thinking)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.3,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.3,"cacheRead":0.15},"blendedRef":0.55,"blendedMin":0.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-thinking/"},{"id":"zhipuai/glm-4.6-original","name":"GLM 4.6 Original","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.35,"output":1.4,"cacheRead":0.175,"official":false},"cheapest":{"provider":"nano-gpt","input":0.35,"output":1.4,"cacheRead":0.175},"blendedRef":0.6125,"blendedMin":0.6125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-original/"},{"id":"zhipuai/glm-5-original","name":"GLM 5 Original","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":3.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":3.2,"cacheRead":0.2},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-11","lastUpdated":"2026-02-11","url":"https://llmpricing.dev/m/zhipuai/glm-5-original/"},{"id":"zhipuai/glm-4.6-turbo-thinking","name":"GLM 4.6 Turbo (Thinking)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":204800,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":3,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":3,"cacheRead":0.5},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-02","lastUpdated":"2025-10-02","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-turbo-thinking/"},{"id":"zhipuai/glm-5.2-thinking","name":"GLM 5.2 Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.42,"output":1.32,"cacheRead":0.078,"official":false},"cheapest":{"provider":"nano-gpt","input":0.42,"output":1.32,"cacheRead":0.078},"blendedRef":0.645,"blendedMin":0.645,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-thinking/"},{"id":"zhipuai/glm-4.7-original","name":"GLM 4.7 Original","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-original/"},{"id":"zhipuai/glm-4.7-original-thinking","name":"GLM 4.7 Original Thinking","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-original-thinking/"},{"id":"meta/mythomax-l2-13b","name":"MythoMax 13B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":4000,"contextRange":[4000,8192],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1003,"output":0.1003,"cacheRead":0.05015,"official":false},"cheapest":{"provider":"openrouter","input":0.06,"output":0.06,"cacheRead":null},"blendedRef":0.1003,"blendedMin":0.06,"blendedTrusted":null,"spread":1.7,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2023-07-02","lastUpdated":"2025-08-08","url":"https://llmpricing.dev/m/meta/mythomax-l2-13b/"},{"id":"thinkingmachines/inkling-small-thinking","name":"Inkling Small Thinking","lab":"thinkingmachines","kind":"video","status":"ga","openWeights":true,"context":524288,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.5,"output":1.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":1.2,"cacheRead":0.1},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-30","lastUpdated":"2026-07-30","url":"https://llmpricing.dev/m/thinkingmachines/inkling-small-thinking/"},{"id":"thinkingmachines/inkling-thinking","name":"Inkling Thinking","lab":"thinkingmachines","kind":"video","status":"ga","openWeights":true,"context":1048000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"nano-gpt","input":1,"output":4.05,"cacheRead":0.17,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":4.05,"cacheRead":0.17},"blendedRef":1.7625,"blendedMin":1.7625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-15","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/thinkingmachines/inkling-thinking/"},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","lab":"thinkingmachines","kind":"video","status":"beta","openWeights":true,"context":262144,"contextRange":[262144,1048576],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"llmtr","input":0.58,"output":1.44,"cacheRead":null,"official":false},"cheapest":{"provider":"deepinfra","input":0.45,"output":1.2,"cacheRead":0.1},"blendedRef":0.795,"blendedMin":0.6375,"blendedTrusted":0.6375,"spread":1.3,"hostCount":11,"pricedHostCount":11,"aa":{"idx":41.2,"coding":52.9,"agentic":31.9,"speed":67,"ttft":1.73,"taskCost":0.0735},"usage":null,"releaseDate":"2026-07-30","lastUpdated":"2026-07-30","url":"https://llmpricing.dev/m/thinkingmachines/inkling-small/"},{"id":"moonshotai/kimi-k2-instruct-fp4","name":"Kimi K2 0711 Instruct FP4","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.8,"cacheRead":0.2},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-07-11","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-instruct-fp4/"},{"id":"openai/inflection-3-pi","name":"Inflection 3 Pi","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.499,"output":9.996,"cacheRead":1.2495,"official":false},"cheapest":{"provider":"nano-gpt","input":2.499,"output":9.996,"cacheRead":1.2495},"blendedRef":4.3733,"blendedMin":4.3733,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-21","lastUpdated":"2024-10-11","url":"https://llmpricing.dev/m/openai/inflection-3-pi/"},{"id":"openai/inflection-3-productivity","name":"Inflection 3 Productivity","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.499,"output":9.996,"cacheRead":1.2495,"official":false},"cheapest":{"provider":"nano-gpt","input":2.499,"output":9.996,"cacheRead":1.2495},"blendedRef":4.3733,"blendedMin":4.3733,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-21","lastUpdated":"2024-10-11","url":"https://llmpricing.dev/m/openai/inflection-3-productivity/"},{"id":"inclusionai/ring-2.6-1t","name":"Ring-2.6-1T","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.3,"output":2.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"openrouter","input":0.075,"output":0.625,"cacheRead":0.015},"blendedRef":0.85,"blendedMin":0.2125,"blendedTrusted":null,"spread":4,"hostCount":4,"pricedHostCount":4,"aa":{"idx":31.7,"coding":42.8,"agentic":20.1,"speed":null,"ttft":null,"taskCost":0.3601},"usage":null,"releaseDate":"2026-05-08","lastUpdated":"2026-05-27","url":"https://llmpricing.dev/m/inclusionai/ring-2.6-1t/"},{"id":"inclusionai/ling-3.0-flash","name":"Ling 3.0 Flash","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.075,"output":0.22,"cacheRead":0.015,"official":false},"cheapest":{"provider":"openrouter","input":0.021,"output":0.063,"cacheRead":0.0042},"blendedRef":0.1112,"blendedMin":0.0315,"blendedTrusted":0.09,"spread":3.6,"hostCount":4,"pricedHostCount":4,"aa":{"idx":37.8,"coding":50.6,"agentic":29.3,"speed":null,"ttft":null,"taskCost":0.0377},"usage":{"rank":21,"tokens":2432021359151,"share":0.009114139287321266},"releaseDate":"2026-07-23","lastUpdated":"2026-08-06","url":"https://llmpricing.dev/m/inclusionai/ling-3.0-flash/"},{"id":"inclusionai/ling-2.6-1t","name":"Ling-2.6-1T","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.3,"output":2.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"openrouter","input":0.075,"output":0.625,"cacheRead":0.015},"blendedRef":0.85,"blendedMin":0.2125,"blendedTrusted":null,"spread":4,"hostCount":4,"pricedHostCount":4,"aa":{"idx":26.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-06-29","url":"https://llmpricing.dev/m/inclusionai/ling-2.6-1t/"},{"id":"inclusionai/ling-3.0-flash-thinking","name":"Ling 3.0 Flash Thinking","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.075,"output":0.22,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nano-gpt","input":0.075,"output":0.22,"cacheRead":0.015},"blendedRef":0.1112,"blendedMin":0.1112,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-23","lastUpdated":"2026-07-23","url":"https://llmpricing.dev/m/inclusionai/ling-3.0-flash-thinking/"},{"id":"inclusionai/ling-2.6-flash","name":"Ling-2.6-flash","lab":"inclusionai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.1,"output":0.3,"cacheRead":0.02,"official":false},"cheapest":{"provider":"openrouter","input":0.01,"output":0.03,"cacheRead":0.002},"blendedRef":0.15,"blendedMin":0.015,"blendedTrusted":null,"spread":10,"hostCount":4,"pricedHostCount":4,"aa":{"idx":14.2,"coding":25.3,"agentic":2.3,"speed":91,"ttft":1.12,"taskCost":null},"usage":{"rank":45,"tokens":579993188835,"share":0.00217355768231623},"releaseDate":"2026-04-21","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/inclusionai/ling-2.6-flash/"},{"id":"mistral/mistral-medium-3.5-thinking","name":"Mistral Medium 3.5 Thinking","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":1.5,"output":7.5,"cacheRead":0.75,"official":false},"cheapest":{"provider":"nano-gpt","input":1.5,"output":7.5,"cacheRead":0.75},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/mistral/mistral-medium-3.5-thinking/"},{"id":"meta/llama-4-maverick","name":"Llama 4 Maverick","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[128000,1048576],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.2,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.35,"blendedMin":0.2625,"blendedTrusted":0.324,"spread":1.3,"hostCount":3,"pricedHostCount":3,"aa":{"idx":14.5,"coding":16.3,"agentic":1.2,"speed":113,"ttft":0.96,"taskCost":0.0357},"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/meta/llama-4-maverick/"},{"id":"meta/llama-4-scout","name":"Llama 4 Scout","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":328000,"contextRange":[328000,1310720],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.085,"output":0.46,"cacheRead":0.0425,"official":false},"cheapest":{"provider":"openrouter","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.1788,"blendedMin":0.15,"blendedTrusted":null,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":{"idx":10.3,"coding":8.2,"agentic":1.1,"speed":135,"ttft":0.78,"taskCost":0.0106},"usage":null,"releaseDate":"2025-09-05","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/meta/llama-4-scout/"},{"id":"mistral/ministral-8b-2512","name":"Ministral 8B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.15,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.11,"output":0.11,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.11,"blendedTrusted":null,"spread":1.4,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-04","lastUpdated":"2025-12-04","url":"https://llmpricing.dev/m/mistral/ministral-8b-2512/"},{"id":"mistral/mixtral-8x22b-instruct-v0.1","name":"Mixtral 8x22B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":64000,"contextRange":[64000,65536],"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":2,"output":6,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":3,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/mistral/mixtral-8x22b-instruct-v0.1/"},{"id":"mistral/mistral-medium-3.1","name":"Mistral Medium 3.1","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[128000,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"mistral","input":0.4,"output":2,"cacheRead":null,"official":true},"cheapest":{"provider":"nano-gpt","input":0.4,"output":2,"cacheRead":0.2},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":{"idx":14.7,"coding":20.5,"agentic":6.1,"speed":106,"ttft":1.47,"taskCost":0.1665},"usage":null,"releaseDate":"2025-09-05","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/mistral/mistral-medium-3.1/"},{"id":"mistral/devstral-2-123b-instruct-2512","name":"Devstral 2 123B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":0.4,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.4,"cacheRead":0.2},"blendedRef":0.8,"blendedMin":0.65,"blendedTrusted":0.8,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-09","lastUpdated":"2026-02-17","url":"https://llmpricing.dev/m/mistral/devstral-2-123b-instruct-2512/"},{"id":"mistral/mistral-large-3-675b-instruct-2512-2","name":"Mistral Large 3 675B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":1,"output":3,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":3,"cacheRead":0.5},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-25","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/mistral/mistral-large-3-675b-instruct-2512-2/"},{"id":"mistral/mistral-small-4-119b-2603-thinking","name":"Mistral Small 4 119B Thinking","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.4,"output":1.4,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.4,"cacheRead":0.2},"blendedRef":0.65,"blendedMin":0.65,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/mistral/mistral-small-4-119b-2603-thinking/"},{"id":"mistral/mistral-small-4-119b-2603-2","name":"Mistral Small 4 119B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"regolo-ai","input":0.75,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1.4,"cacheRead":0.2},"blendedRef":1.3125,"blendedMin":0.65,"blendedTrusted":null,"spread":1.9,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/mistral/mistral-small-4-119b-2603-2/"},{"id":"mistral/ministral-3b-2512","name":"Ministral 3B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.04,"output":0.04,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.04,"blendedTrusted":0.04,"spread":2.5,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2025-12-04","url":"https://llmpricing.dev/m/mistral/ministral-3b-2512/"},{"id":"mistral/mistral-large","name":"Mistral Large 2411","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.006,"output":6.001,"cacheRead":0.2,"official":false},"cheapest":{"provider":"nano-gpt","input":2.006,"output":6.001,"cacheRead":0.2},"blendedRef":3.0047,"blendedMin":3.0047,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-02-26","url":"https://llmpricing.dev/m/mistral/mistral-large/"},{"id":"mistral/devstral-small-2505","name":"Mistral Devstral Small 2505","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.06,"output":0.06,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.06,"output":0.06,"cacheRead":0.03},"blendedRef":0.06,"blendedMin":0.06,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-02","lastUpdated":"2025-08-02","url":"https://llmpricing.dev/m/mistral/devstral-small-2505/"},{"id":"mistral/ministral-14b-2512","name":"Ministral 14B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":0.2,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-04","url":"https://llmpricing.dev/m/mistral/ministral-14b-2512/"},{"id":"mistral/mistral-nemo","name":"Mistral Nemo","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[16384,131072],"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":0.15,"output":0.15,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.019,"output":0.03,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.0217,"blendedTrusted":0.15,"spread":1052.6,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":{"rank":47,"tokens":569214657295,"share":0.002133164518251816},"releaseDate":"2024-07-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/mistral-nemo/"},{"id":"mistral/ministral-14b-instruct-2512-2","name":"Ministral 3 14B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.05},"blendedRef":0.2,"blendedMin":0.175,"blendedTrusted":0.2,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":{"idx":11.2,"coding":14.4,"agentic":2.2,"speed":94,"ttft":0.84,"taskCost":0.1584},"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/mistral/ministral-14b-instruct-2512-2/"},{"id":"mistral/mistral-saba","name":"Mistral Saba","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[32000,32768],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":0.2,"output":0.6,"cacheRead":0.02,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1989,"output":0.595,"cacheRead":0.09945},"blendedRef":0.3,"blendedMin":0.2979,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":6.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-02-17","url":"https://llmpricing.dev/m/mistral/mistral-saba/"},{"id":"crofai/greg-2-ultra","name":"Greg 2 Ultra","lab":"crofai","kind":"text","status":"ga","openWeights":false,"context":229376,"contextRange":null,"outputLimit":229376,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"crof","input":3,"output":10,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":10,"cacheRead":0.5},"blendedRef":4.75,"blendedMin":4.75,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-19","lastUpdated":"2026-06-19","url":"https://llmpricing.dev/m/crofai/greg-2-ultra/"},{"id":"crofai/greg-2-super","name":"Greg 2 Super","lab":"crofai","kind":"text","status":"ga","openWeights":false,"context":229376,"contextRange":null,"outputLimit":229376,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"crof","input":1.5,"output":5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"nano-gpt","input":1.5,"output":5,"cacheRead":0.25},"blendedRef":2.375,"blendedMin":2.375,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-19","lastUpdated":"2026-06-19","url":"https://llmpricing.dev/m/crofai/greg-2-super/"},{"id":"amazon/nova-pro-v1-2","name":"Amazon Nova Pro 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":5120,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.8,"output":3.2,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.799,"output":3.196,"cacheRead":0.3995},"blendedRef":1.4,"blendedMin":1.3983,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/amazon/nova-pro-v1-2/"},{"id":"amazon/nova-2-lite-v1","name":"Amazon Nova 2 Lite","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"nano-gpt","input":0.51,"output":4.25,"cacheRead":0.255,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":2.5,"cacheRead":null},"blendedRef":1.445,"blendedMin":0.85,"blendedTrusted":null,"spread":1.7,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/amazon/nova-2-lite-v1/"},{"id":"amazon/nova-micro-v1","name":"Amazon Nova Micro 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":5120,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.0357,"output":0.1394,"cacheRead":0.01785,"official":false},"cheapest":{"provider":"kilo","input":0.035,"output":0.14,"cacheRead":null},"blendedRef":0.0616,"blendedMin":0.0613,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/amazon/nova-micro-v1/"},{"id":"amazon/nova-lite-v1","name":"Amazon Nova Lite 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":5120,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.0595,"output":0.238,"cacheRead":0.02975},"blendedRef":0.105,"blendedMin":0.1041,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/amazon/nova-lite-v1/"},{"id":"mistral/mn-loosecannon-12b-v1","name":"MN-LooseCannon-12B-v1","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465,"official":false},"cheapest":{"provider":"nano-gpt","input":0.493,"output":0.493,"cacheRead":0.2465},"blendedRef":0.493,"blendedMin":0.493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/mn-loosecannon-12b-v1/"},{"id":"meta/magnum-v4-72b","name":"Magnum v4 72B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[16384,32768],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":3,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":2.006,"output":2.992,"cacheRead":1.003},"blendedRef":3.5,"blendedMin":2.2525,"blendedTrusted":null,"spread":1.5,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/meta/magnum-v4-72b/"},{"id":"meta/magnum-v2-72b","name":"Magnum V2 72B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2.006,"output":2.992,"cacheRead":1.003,"official":false},"cheapest":{"provider":"nano-gpt","input":2.006,"output":2.992,"cacheRead":1.003},"blendedRef":2.2525,"blendedMin":2.2525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/meta/magnum-v2-72b/"},{"id":"nex-agi/nex-n2-mini","name":"Nex N2 Mini","lab":"nex-agi","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.025,"output":0.1,"cacheRead":0.0025,"official":false},"cheapest":{"provider":"nano-gpt","input":0.025,"output":0.1,"cacheRead":0.0025},"blendedRef":0.0438,"blendedMin":0.0438,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":{"rank":67,"tokens":29557756433,"share":0.00011076938454402448},"releaseDate":"2026-06-24","lastUpdated":"2026-06-24","url":"https://llmpricing.dev/m/nex-agi/nex-n2-mini/"},{"id":"nex-agi/nex-n2-pro","name":"Nex N2 Pro","lab":"nex-agi","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.5,"output":2.5,"cacheRead":0.25,"official":false},"cheapest":{"provider":"openrouter","input":0.25,"output":1,"cacheRead":0.025},"blendedRef":1,"blendedMin":0.4375,"blendedTrusted":null,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":{"idx":41.7,"coding":59.1,"agentic":31.2,"speed":138,"ttft":1.61,"taskCost":null},"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/nex-agi/nex-n2-pro/"},{"id":"upstage/solar-pro3","name":"Solar Pro 3","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[128000,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"upstage","input":0.25,"output":0.25,"cacheRead":null,"official":true},"cheapest":{"provider":"upstage","input":0.25,"output":0.25,"cacheRead":null},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":1.7,"hostCount":4,"pricedHostCount":4,"aa":{"idx":14.5,"coding":16.2,"agentic":2.9,"speed":152,"ttft":2.38,"taskCost":0.1457},"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/upstage/solar-pro3/"},{"id":"upstage/solar-pro4-thinking","name":"Solar Pro 4 Thinking","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":524288,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.03,"output":0.12,"cacheRead":0.006,"official":false},"cheapest":{"provider":"nano-gpt","input":0.03,"output":0.12,"cacheRead":0.006},"blendedRef":0.0525,"blendedMin":0.0525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-06","lastUpdated":"2026-08-06","url":"https://llmpricing.dev/m/upstage/solar-pro4-thinking/"},{"id":"upstage/solar-pro4","name":"Solar Pro 4","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":524288,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"upstage","input":0.3,"output":1.2,"cacheRead":0.06,"official":true},"cheapest":{"provider":"nano-gpt","input":0.03,"output":0.12,"cacheRead":0.006},"blendedRef":0.525,"blendedMin":0.0525,"blendedTrusted":null,"spread":10,"hostCount":4,"pricedHostCount":4,"aa":{"idx":41.6,"coding":52.7,"agentic":33.6,"speed":47,"ttft":2.53,"taskCost":0.2231},"usage":{"rank":43,"tokens":610416924365,"share":0.0022875723731073682},"releaseDate":"2026-08-06","lastUpdated":"2026-08-06","url":"https://llmpricing.dev/m/upstage/solar-pro4/"},{"id":"meta/lumimaid-v0.2-70b","name":"Lumimaid v0.2","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1,"output":1.5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1,"output":1.5,"cacheRead":0.5},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/meta/lumimaid-v0.2-70b/"},{"id":"zhipuai/glm-4-9b-0414","name":"GLM 4 9B 0414","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/zhipuai/glm-4-9b-0414/"},{"id":"zhipuai/glm-z1-9b-0414","name":"GLM Z1 9B 0414","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/zhipuai/glm-z1-9b-0414/"},{"id":"zhipuai/glm-4-32b-0414","name":"GLM 4 32B 0414","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.2,"cacheRead":0.1},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/zhipuai/glm-4-32b-0414/"},{"id":"nvidia/openreasoning-nemotron-32b","name":"OpenReasoning Nemotron 32B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.4,"cacheRead":0.05},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/nvidia/openreasoning-nemotron-32b/"},{"id":"kwaipilot/kat-coder-pro-v2.5","name":"KAT Coder Pro V2.5","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.74,"output":2.96,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.74,"output":2.96,"cacheRead":0.15},"blendedRef":1.295,"blendedMin":1.295,"blendedTrusted":1.295,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-10","lastUpdated":"2026-07-14","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-pro-v2.5/"},{"id":"kwaipilot/kat-coder-air-v2.5","name":"KAT Coder Air V2.5","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.15,"output":0.6,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.6,"cacheRead":0.03},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-10","lastUpdated":"2026-07-14","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-air-v2.5/"},{"id":"kwaipilot/kat-coder-pro-v2","name":"KAT Coder Pro V2","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,262144],"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.15},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":0.525,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":{"idx":33.7,"coding":59.5,"agentic":15.1,"speed":107,"ttft":1.38,"taskCost":null},"usage":null,"releaseDate":"2026-03-27","lastUpdated":"2026-03-30","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-pro-v2/"},{"id":"ibm-granite/granite-4.1-8b","name":"Granite 4.1 8B","lab":"ibm-granite","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.05,"output":0.1,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.05,"output":0.1,"cacheRead":0.05},"blendedRef":0.0625,"blendedMin":0.0625,"blendedTrusted":0.0625,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":{"idx":6.4,"coding":9.5,"agentic":null,"speed":115,"ttft":0.77,"taskCost":null},"usage":null,"releaseDate":"2026-04-29","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/ibm-granite/granite-4.1-8b/"},{"id":"alibaba/qwen2.5-vl-72b-instruct","name":"Qwen2.5 VL 72B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35,"official":false},"cheapest":{"provider":"nano-gpt","input":0.7,"output":0.7,"cacheRead":0.35},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-02-01","url":"https://llmpricing.dev/m/alibaba/qwen2.5-vl-72b-instruct/"},{"id":"moonshotai/kimi-k2.7-code-2","name":"Kimi K2.7 Code TEE","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.95,"output":4,"cacheRead":0.19,"official":false},"cheapest":{"provider":"nano-gpt","input":0.95,"output":4,"cacheRead":0.19},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-2/"},{"id":"moonshotai/kimi-k3-2","name":"Kimi K3 TEE","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"chutes","input":3,"output":15,"cacheRead":0.29999999999999993,"official":false},"cheapest":{"provider":"nano-gpt","input":3,"output":15,"cacheRead":1.5},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-29","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-2/"},{"id":"zhipuai/glm-4.7-3","name":"GLM 4.7 TEE","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.85,"output":3.3,"cacheRead":0.425,"official":false},"cheapest":{"provider":"nano-gpt","input":0.85,"output":3.3,"cacheRead":0.425},"blendedRef":1.4625,"blendedMin":1.4625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-3/"},{"id":"deepseek/deepseek-v4-flash-2","name":"DeepSeek V4 Flash TEE","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.4,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.4,"cacheRead":0.04},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-2/"},{"id":"meta/llama3-3-70b","name":"Llama 3.3 70B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.75,"output":2.75,"cacheRead":1.75,"official":false},"cheapest":{"provider":"stackit","input":0.53,"output":0.76,"cacheRead":null},"blendedRef":2,"blendedMin":0.5875,"blendedTrusted":0.5875,"spread":3.3,"hostCount":6,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/meta/llama3-3-70b/"},{"id":"alibaba/qwen3.5-397b-a17b-2","name":"Qwen3.5 397B A17B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.55,"output":3.5,"cacheRead":0.275,"official":false},"cheapest":{"provider":"chutes","input":0.45,"output":3,"cacheRead":0.04499999999999999},"blendedRef":1.2875,"blendedMin":1.0875,"blendedTrusted":1.0875,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-15","lastUpdated":"2026-02-15","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-a17b-2/"},{"id":"zhipuai/glm-5.1-thinking-2","name":"GLM 5.1 Thinking TEE","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.5,"output":5.25,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":1.5,"output":5.25,"cacheRead":0.3},"blendedRef":2.4375,"blendedMin":2.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-thinking-2/"},{"id":"deepseek/deepseek-v3.2-2","name":"DeepSeek V3.2 TEE","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[131072,164000],"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"chutes","input":1,"output":1,"cacheRead":0.09999999999999998,"official":false},"cheapest":{"provider":"nano-gpt","input":0.5,"output":1,"cacheRead":0.25},"blendedRef":1,"blendedMin":0.625,"blendedTrusted":1,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2026-06-21","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-2/"},{"id":"google/gemma-4-31b-it-2","name":"Gemma 4 31B IT TEE","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.46,"cacheRead":0.075,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.46,"cacheRead":0.075},"blendedRef":0.2275,"blendedMin":0.2275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-2/"},{"id":"meta/muse-glimmer-30b-2","name":"Muse Glimmer 30B TEE","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.35,"output":1.5,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nano-gpt","input":0.35,"output":1.5,"cacheRead":0.04},"blendedRef":0.6375,"blendedMin":0.6375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-10","lastUpdated":"2026-08-10","url":"https://llmpricing.dev/m/meta/muse-glimmer-30b-2/"},{"id":"openai/gpt-oss-120b-2","name":"GPT-OSS 120B TEE","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":2,"output":2,"cacheRead":2,"official":false},"cheapest":{"provider":"nano-gpt","input":2,"output":2,"cacheRead":2},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-2/"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B TEE","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-03-10","url":"https://llmpricing.dev/m/google/gemma-3-27b-it/"},{"id":"zhipuai/glm-5.2-2","name":"GLM 5.2 TEE","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.4,"output":4.6,"cacheRead":0.5,"official":false},"cheapest":{"provider":"chutes","input":1.25,"output":3.95,"cacheRead":0.12499999999999997},"blendedRef":2.2,"blendedMin":1.925,"blendedTrusted":1.925,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-2/"},{"id":"google/gemma4-31b-thinking","name":"Gemma 4 31B Thinking TEE","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.4,"output":1,"cacheRead":0.4,"official":false},"cheapest":{"provider":"nano-gpt","input":0.4,"output":1,"cacheRead":0.4},"blendedRef":0.55,"blendedMin":0.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-02","lastUpdated":"2026-05-02","url":"https://llmpricing.dev/m/google/gemma4-31b-thinking/"},{"id":"alibaba/qwen3.6-35b-a3b-2","name":"Qwen3.6 35B A3B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":1.27,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":1.27,"cacheRead":0.1},"blendedRef":0.4675,"blendedMin":0.4675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-2/"},{"id":"alibaba/qwen3.6-27b-2","name":"Qwen3.6 27B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.32,"output":2.7,"cacheRead":0.16,"official":false},"cheapest":{"provider":"chutes","input":0.3,"output":2,"cacheRead":0.029999999999999992},"blendedRef":0.915,"blendedMin":0.725,"blendedTrusted":0.725,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/alibaba/qwen3.6-27b-2/"},{"id":"google/gemma-4-26b-a4b-uncensored","name":"Gemma 4 26B A4B Uncensored TEE","lab":"google","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.15,"output":0.7,"cacheRead":0.075,"official":false},"cheapest":{"provider":"nano-gpt","input":0.15,"output":0.7,"cacheRead":0.075},"blendedRef":0.2875,"blendedMin":0.2875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-23","lastUpdated":"2026-05-23","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-uncensored/"},{"id":"alibaba/qwen3.5-27b-2","name":"Qwen3.5 27B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":0.3,"output":2.4,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":2.4,"cacheRead":0.15},"blendedRef":0.825,"blendedMin":0.825,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-27b-2/"},{"id":"zhipuai/glm-5.1-2","name":"GLM 5.1 TEE","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.5,"output":5.25,"cacheRead":0.3,"official":false},"cheapest":{"provider":"chutes","input":0.98,"output":3.08,"cacheRead":0.09799999999999998},"blendedRef":2.4375,"blendedMin":1.505,"blendedTrusted":1.505,"spread":1.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-2/"},{"id":"alibaba/qwen3.6-35b-a3b-uncensored","name":"Qwen3.6 35B A3B Uncensored TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.5,"cacheRead":0.15,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.5,"cacheRead":0.15},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-23","lastUpdated":"2026-05-23","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-uncensored/"},{"id":"zhipuai/glm-5.2-thinking-2","name":"GLM 5.2 Thinking TEE","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":1.4,"output":4.6,"cacheRead":0.5,"official":false},"cheapest":{"provider":"nano-gpt","input":1.4,"output":4.6,"cacheRead":0.5},"blendedRef":2.2,"blendedMin":2.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-thinking-2/"},{"id":"alibaba/qwen3.5-122b-a10b-2","name":"Qwen3.5 122B A10B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.46,"output":3.68,"cacheRead":0.23,"official":false},"cheapest":{"provider":"nano-gpt","input":0.46,"output":3.68,"cacheRead":0.23},"blendedRef":1.265,"blendedMin":1.265,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-122b-a10b-2/"},{"id":"openai/gpt-oss-20b-2","name":"GPT-OSS 20B TEE","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1,"official":false},"cheapest":{"provider":"nano-gpt","input":0.2,"output":0.8,"cacheRead":0.1},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-20b-2/"},{"id":"moonshotai/kimi-k2.6-2","name":"Kimi K2.6 TEE","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"nano-gpt","input":1.5,"output":5.25,"cacheRead":0.375,"official":false},"cheapest":{"provider":"chutes","input":0.58,"output":3.4,"cacheRead":0.05799999999999998},"blendedRef":2.4375,"blendedMin":1.285,"blendedTrusted":1.285,"spread":2.6,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-2/"},{"id":"dots-studio/dots-3-note-preview","name":"Dots3-Note Preview","lab":"dots-studio","kind":"text","status":"ga","openWeights":true,"context":393216,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1,"output":0.2,"cacheRead":0.05},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-15","lastUpdated":"2026-08-15","url":"https://llmpricing.dev/m/dots-studio/dots-3-note-preview/"},{"id":"minimax/minimax-01","name":"MiniMax 01","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":1000192,"contextRange":null,"outputLimit":1000192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","pdf","image"],"reference":{"provider":"openrouter","input":0.2,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"nano-gpt","input":0.1394,"output":1.122,"cacheRead":0.0697},"blendedRef":0.425,"blendedMin":0.3851,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-01-15","url":"https://llmpricing.dev/m/minimax/minimax-01/"},{"id":"minimax/MiniMax-M2-Her","name":"MiniMax-M2 Her","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":65532,"contextRange":[65532,200000],"outputLimit":2048,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.302,"output":1.207,"cacheRead":0.151,"official":false},"cheapest":{"provider":"openrouter","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":0.5283,"blendedMin":0.525,"blendedTrusted":null,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-01-23","lastUpdated":"2026-01-23","url":"https://llmpricing.dev/m/minimax/MiniMax-M2-Her/"},{"id":"minimax/minimax-latest","name":"MiniMax Latest","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":512000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-03","lastUpdated":"2026-05-03","url":"https://llmpricing.dev/m/minimax/minimax-latest/"},{"id":"minimax/minimax-m3-thinking","name":"MiniMax M3 Thinking","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":512000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"nano-gpt","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/minimax/minimax-m3-thinking/"},{"id":"minimax/minimax-m2.7-turbo","name":"MiniMax M2.7 Turbo","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nano-gpt","input":0.6,"output":2.4,"cacheRead":0.3,"official":false},"cheapest":{"provider":"nano-gpt","input":0.6,"output":2.4,"cacheRead":0.3},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/minimax-m2.7-turbo/"},{"id":"nvidia/nemotron-3-super-120b-a12b-3","name":"Nemotron 3 Super 120B A12B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[8000,1048576],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"synthetic","input":0.3,"output":1,"cacheRead":0.3,"official":false},"cheapest":{"provider":"openrouter","input":0.085,"output":0.4,"cacheRead":null},"blendedRef":0.475,"blendedMin":0.1638,"blendedTrusted":0.45,"spread":3.5,"hostCount":10,"pricedHostCount":8,"aa":{"idx":25.7,"coding":37.7,"agentic":8.8,"speed":129,"ttft":2,"taskCost":0.2286},"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b-3/"},{"id":"tencent/hy3-2","name":"Hy3","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[202752,262144],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tencent-tokenhub","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":{"provider":"requesty","input":0.126,"output":0.522,"cacheRead":0.0315},"blendedRef":0,"blendedMin":0.225,"blendedTrusted":0.231,"spread":1.3,"hostCount":11,"pricedHostCount":9,"aa":{"idx":42.2,"coding":58.8,"agentic":31.4,"speed":67,"ttft":2.88,"taskCost":0.0357},"usage":{"rank":1,"tokens":31791464968265,"share":0.11914033516955291},"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3-2/"},{"id":"misc/abliterated-model-large","name":"Abliterated Model Large","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":999990,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abliteration-ai","input":5,"output":5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"abliteration-ai","input":5,"output":5,"cacheRead":0.5},"blendedRef":5,"blendedMin":5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-25","lastUpdated":"2026-07-28","url":"https://llmpricing.dev/m/misc/abliterated-model-large/"},{"id":"misc/abliterated-model","name":"Abliterated Model","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":150000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"abliteration-ai","input":3,"output":3,"cacheRead":0.3,"official":false},"cheapest":{"provider":"abliteration-ai","input":3,"output":3,"cacheRead":0.3},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-06","lastUpdated":"2026-07-28","url":"https://llmpricing.dev/m/misc/abliterated-model/"},{"id":"openai/green-r-raw","name":"Green R Raw","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"greenpt","input":0.399,"output":1.083,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.399,"output":1.083,"cacheRead":null},"blendedRef":0.57,"blendedMin":0.57,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/green-r-raw/"},{"id":"mistral/mistral-small-2506","name":"Mistral Small 3.2","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":0.1,"output":0.3,"cacheRead":null,"official":true},"cheapest":{"provider":"helicone","input":0.075,"output":0.2,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.1063,"blendedTrusted":0.15,"spread":3,"hostCount":4,"pricedHostCount":4,"aa":{"idx":10.7,"coding":12.5,"agentic":2.1,"speed":151,"ttft":0.86,"taskCost":0.1403},"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2025-06-20","url":"https://llmpricing.dev/m/mistral/mistral-small-2506/"},{"id":"zhipuai/glm-5.2-ponytail-lite","name":"GLM-5.2 Ponytail Lite","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-ponytail-lite/"},{"id":"zhipuai/glm-5.2-ponytail-ultra","name":"GLM-5.2 Ponytail Ultra","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-ponytail-ultra/"},{"id":"misc/holo2-30b-a3b","name":"Holo2 30B A3B","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":22016,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"greenpt","input":0.399,"output":0.969,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.399,"output":0.969,"cacheRead":null},"blendedRef":0.5415,"blendedMin":0.5415,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11","lastUpdated":"2025-11","url":"https://llmpricing.dev/m/misc/holo2-30b-a3b/"},{"id":"misc/green-s","name":"Green S","lab":"misc","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"greenpt","input":0.00437,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.00437,"output":0,"cacheRead":null},"blendedRef":0.0033,"blendedMin":0.0033,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01","lastUpdated":"2025-01","url":"https://llmpricing.dev/m/misc/green-s/"},{"id":"mistral/green-l-raw","name":"Green L Raw","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"greenpt","input":0.285,"output":0.912,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.285,"output":0.912,"cacheRead":null},"blendedRef":0.4418,"blendedMin":0.4418,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2025-06-20","url":"https://llmpricing.dev/m/mistral/green-l-raw/"},{"id":"zhipuai/glm-5.2-caveman-ultra","name":"GLM-5.2 Caveman Ultra","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-caveman-ultra/"},{"id":"zhipuai/glm-5.2-caveman-lite","name":"GLM-5.2 Caveman Lite","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-caveman-lite/"},{"id":"misc/green-s-pro","name":"Green S Pro","lab":"misc","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"greenpt","input":0.00437,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.00437,"output":0,"cacheRead":null},"blendedRef":0.0033,"blendedMin":0.0033,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02","lastUpdated":"2025-02","url":"https://llmpricing.dev/m/misc/green-s-pro/"},{"id":"openai/green-r","name":"Green R","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"greenpt","input":0.399,"output":1.083,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.399,"output":1.083,"cacheRead":null},"blendedRef":0.57,"blendedMin":0.57,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/green-r/"},{"id":"zhipuai/glm-5.2-caveman","name":"GLM-5.2 Caveman","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-caveman/"},{"id":"google/gemma-3-27b-it-2","name":"Gemma 3 27B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":37000,"contextRange":[37000,262144],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"stackit","input":0.53,"output":0.76,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.119,"output":0.2,"cacheRead":null},"blendedRef":0.5875,"blendedMin":0.1392,"blendedTrusted":0.5875,"spread":6.6,"hostCount":5,"pricedHostCount":5,"aa":{"idx":7.4,"coding":10.1,"agentic":0.3,"speed":null,"ttft":null,"taskCost":0},"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-05-17","url":"https://llmpricing.dev/m/google/gemma-3-27b-it-2/"},{"id":"google/gemma4","name":"Gemma 4","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[131072,262144],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmtr","input":2,"output":5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":0.18,"output":0.5,"cacheRead":0.036},"blendedRef":2.75,"blendedMin":0.26,"blendedTrusted":0.26,"spread":11.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/google/gemma4/"},{"id":"mistral/voxtral-small-24b-2507","name":"Voxtral Small 24B","lab":"mistral","kind":"audio","status":"ga","openWeights":true,"context":32768,"contextRange":[32000,32768],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"greenpt","input":0.228,"output":0.513,"cacheRead":null,"official":false},"cheapest":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null},"blendedRef":0.2993,"blendedMin":0.0023,"blendedTrusted":0.0023,"spread":99.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-15","lastUpdated":"2025-07-15","url":"https://llmpricing.dev/m/mistral/voxtral-small-24b-2507/"},{"id":"zhipuai/glm-5.2-honey-lite","name":"GLM-5.2 Honey Lite","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-honey-lite/"},{"id":"mistral/green-l","name":"Green L","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"greenpt","input":0.285,"output":0.912,"cacheRead":null,"official":false},"cheapest":{"provider":"greenpt","input":0.285,"output":0.912,"cacheRead":null},"blendedRef":0.4418,"blendedMin":0.4418,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2025-06-20","url":"https://llmpricing.dev/m/mistral/green-l/"},{"id":"zhipuai/glm-5.2-ponytail","name":"GLM-5.2 Ponytail","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-ponytail/"},{"id":"zhipuai/glm-5.2-honey-ultra","name":"GLM-5.2 Honey Ultra","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-honey-ultra/"},{"id":"zhipuai/glm-5.2-honey","name":"GLM-5.2 Honey","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135,"official":false},"cheapest":{"provider":"greenpt","input":1.254,"output":5.016,"cacheRead":0.3135},"blendedRef":2.1945,"blendedMin":2.1945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-honey/"},{"id":"mistral/pixtral-12b","name":"Pixtral 12B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":0.15,"output":0.15,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1.9,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-09-01","lastUpdated":"2024-09-01","url":"https://llmpricing.dev/m/mistral/pixtral-12b/"},{"id":"openai/gpt-5.6","name":"GPT-5.6","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":[372000,1050000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":5,"output":30,"cacheRead":0.5,"official":true},"cheapest":{"provider":"xpersona","input":1.5,"output":12,"cacheRead":0.15},"blendedRef":11.25,"blendedMin":4.125,"blendedTrusted":11.25,"spread":3.3,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6/"},{"id":"misc/xpersona-frieren-coder","name":"Xpersona Frieren 1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"xpersona","input":1.5,"output":6,"cacheRead":0.15,"official":false},"cheapest":{"provider":"xpersona","input":1.5,"output":6,"cacheRead":0.15},"blendedRef":2.625,"blendedMin":2.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-05-25","url":"https://llmpricing.dev/m/misc/xpersona-frieren-coder/"},{"id":"tencent/hy3-preview","name":"Hy3 preview","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tencent-tokenhub","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":{"provider":"siliconflow","input":0.066,"output":0.26,"cacheRead":0.029},"blendedRef":0,"blendedMin":0.1145,"blendedTrusted":0.1145,"spread":2.7,"hostCount":6,"pricedHostCount":5,"aa":{"idx":34.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-04-20","lastUpdated":"2026-04-20","url":"https://llmpricing.dev/m/tencent/hy3-preview/"},{"id":"misc/step-router-v1","name":"Step Router v1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/misc/step-router-v1/"},{"id":"xiaomi/mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","lab":"xiaomi","kind":"audio","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi-token-plan-sgp","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-tts-voicedesign/"},{"id":"xiaomi/mimo-v2-tts","name":"MiMo-V2-TTS","lab":"xiaomi","kind":"audio","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi-token-plan-sgp","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-tts/"},{"id":"xiaomi/mimo-v2-pro","name":"MiMo-V2-Pro","lab":"xiaomi","kind":"text","status":"deprecated","openWeights":false,"context":1048576,"contextRange":[1000000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi","input":0.435,"output":0.87,"cacheRead":0.0036,"official":true},"cheapest":{"provider":"xiaomi","input":0.435,"output":0.87,"cacheRead":0.0036},"blendedRef":0.5438,"blendedMin":0.5438,"blendedTrusted":0.5438,"spread":4.6,"hostCount":8,"pricedHostCount":5,"aa":{"idx":41.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-pro/"},{"id":"xiaomi/mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","lab":"xiaomi","kind":"audio","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi-token-plan-sgp","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-tts-voiceclone/"},{"id":"xiaomi/mimo-v2.5-tts","name":"MiMo-V2.5-TTS","lab":"xiaomi","kind":"audio","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi-token-plan-sgp","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-tts/"},{"id":"misc/code-prime","name":"Code Prime","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":196608,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-04","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/misc/code-prime/"},{"id":"misc/text-prime","name":"Text Prime","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":196608,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/misc/text-prime/"},{"id":"misc/text-standard","name":"Text Standard","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/misc/text-standard/"},{"id":"misc/agent-prime","name":"Agent Prime","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":196608,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-04","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/misc/agent-prime/"},{"id":"misc/agent-max","name":"Agent Max","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-04","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/misc/agent-max/"},{"id":"misc/code-standard","name":"Code Standard","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-04","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/misc/code-standard/"},{"id":"misc/text-max","name":"Text Max","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/misc/text-max/"},{"id":"misc/code-max","name":"Code Max","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-04","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/misc/code-max/"},{"id":"misc/agent-standard","name":"Agent Standard","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-04","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/misc/agent-standard/"},{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","lab":"google","kind":"image","status":"ga","openWeights":false,"context":65536,"contextRange":[65536,1048576],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"google-vertex","input":2,"output":120,"cacheRead":0.2,"official":true},"cheapest":{"provider":"requesty","input":1.8,"output":10.8,"cacheRead":0.18},"blendedRef":31.5,"blendedMin":4.05,"blendedTrusted":4.5,"spread":1.1,"hostCount":16,"pricedHostCount":16,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/google/gemini-3-pro-image/"},{"id":"google/gemini-2.5-flash-tts","name":"Gemini 2.5 Flash TTS","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google-vertex","input":0.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"google-vertex","input":0.5,"output":10,"cacheRead":null},"blendedRef":2.875,"blendedMin":2.875,"blendedTrusted":2.875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-12-10","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-tts/"},{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","lab":"google","kind":"embedding","status":"ga","openWeights":false,"context":2048,"contextRange":[2048,8192],"outputLimit":1,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google-vertex","input":0.15,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"google-vertex","input":0.15,"output":0,"cacheRead":null},"blendedRef":0.1125,"blendedMin":0.1125,"blendedTrusted":0.1125,"spread":1,"hostCount":5,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/google/gemini-embedding-001/"},{"id":"google/gemini-2.5-pro-tts","name":"Gemini 2.5 Pro TTS","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google-vertex","input":1,"output":20,"cacheRead":null,"official":true},"cheapest":{"provider":"google-vertex","input":1,"output":20,"cacheRead":null},"blendedRef":5.75,"blendedMin":5.75,"blendedTrusted":5.75,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-12-10","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-tts/"},{"id":"anthropic/claude-opus-4-20250514-2","name":"Claude Opus 4","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":[192512,200000],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":15,"output":75,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":13,"output":64,"cacheRead":1.3},"blendedRef":30,"blendedMin":25.75,"blendedTrusted":30,"spread":1.2,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-20250514-2/"},{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","lab":"google","kind":"image","status":"ga","openWeights":false,"context":131072,"contextRange":[65536,1048576],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"google-vertex","input":0.5,"output":60,"cacheRead":0.05,"official":true},"cheapest":{"provider":"requesty","input":0.45,"output":1.8,"cacheRead":null},"blendedRef":15.375,"blendedMin":0.7875,"blendedTrusted":1.125,"spread":1.1,"hostCount":15,"pricedHostCount":15,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-image/"},{"id":"anthropic/claude-sonnet-4-20250514-2","name":"Claude Sonnet 4","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":[200000,1000000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":2.6,"output":13,"cacheRead":0.26},"blendedRef":6,"blendedMin":5.2,"blendedTrusted":6,"spread":1.2,"hostCount":11,"pricedHostCount":11,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-20250514-2/"},{"id":"google/gemini-2.5-flash-image-2","name":"Nano Banana","lab":"google","kind":"image","status":"ga","openWeights":false,"context":32768,"contextRange":[32768,65536],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"google-vertex","input":0.3,"output":30,"cacheRead":null,"official":true},"cheapest":{"provider":"poe","input":0.21,"output":1.8,"cacheRead":0.021},"blendedRef":7.725,"blendedMin":0.6075,"blendedTrusted":7.725,"spread":1.4,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-image-2/"},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[196608,200000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"anthropic","input":5,"output":25,"cacheRead":0.5,"official":true},"cheapest":{"provider":"qihang-ai","input":0.71,"output":3.57,"cacheRead":null},"blendedRef":10,"blendedMin":1.425,"blendedTrusted":10,"spread":8.5,"hostCount":17,"pricedHostCount":17,"aa":{"idx":41.9,"coding":null,"agentic":null,"speed":46,"ttft":11.19,"taskCost":null},"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2025-11-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-20251101/"},{"id":"anthropic/claude-opus-4-1-20250805","name":"Claude Opus 4.1","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":[196608,200000],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":15,"output":75,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":13,"output":64,"cacheRead":1.3},"blendedRef":30,"blendedMin":25.75,"blendedTrusted":30,"spread":1.2,"hostCount":11,"pricedHostCount":11,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-20250805/"},{"id":"alibaba/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","lab":"alibaba","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"impossibl","input":2.5,"output":7.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":1.815,"output":5.4461,"cacheRead":0.21},"blendedRef":3.75,"blendedMin":2.7228,"blendedTrusted":null,"spread":1.4,"hostCount":5,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-19","lastUpdated":"2026-07-19","url":"https://llmpricing.dev/m/alibaba/qwen3.8-max-preview/"},{"id":"misc/wan2.7-image","name":"Wan2.7 Image","lab":"misc","kind":"image","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/misc/wan2.7-image/"},{"id":"misc/happyhorse-1.1-i2v","name":"HappyHorse 1.1 Image-to-Video","lab":"misc","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-17","lastUpdated":"2026-07-17","url":"https://llmpricing.dev/m/misc/happyhorse-1.1-i2v/"},{"id":"misc/happyhorse-1.1-r2v","name":"HappyHorse 1.1 Reference-to-Video","lab":"misc","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-17","lastUpdated":"2026-07-17","url":"https://llmpricing.dev/m/misc/happyhorse-1.1-r2v/"},{"id":"alibaba/qwen-image-2.0","name":"Qwen Image 2.0","lab":"alibaba","kind":"image","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/alibaba/qwen-image-2.0/"},{"id":"alibaba/qwen-image-2.0-pro","name":"Qwen Image 2.0 Pro","lab":"alibaba","kind":"image","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/alibaba/qwen-image-2.0-pro/"},{"id":"misc/wan2.7-image-pro","name":"Wan2.7 Image Pro","lab":"misc","kind":"image","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/misc/wan2.7-image-pro/"},{"id":"misc/happyhorse-1.1-t2v","name":"HappyHorse 1.1 Text-to-Video","lab":"misc","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-token-plan","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-17","lastUpdated":"2026-07-17","url":"https://llmpricing.dev/m/misc/happyhorse-1.1-t2v/"},{"id":"google/gemini-3.1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google","input":1,"output":20,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":1,"output":20,"cacheRead":null},"blendedRef":5.75,"blendedMin":5.75,"blendedTrusted":5.75,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-15","lastUpdated":"2026-04-15","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-tts-preview/"},{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","lab":"google","kind":"image","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"google","input":0.25,"output":30,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.25,"output":1.5,"cacheRead":null},"blendedRef":7.6875,"blendedMin":0.5625,"blendedTrusted":7.6875,"spread":1,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite-image/"},{"id":"google/deep-research-preview-04-2026","name":"Deep Research Preview (Apr-21-2026)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google","input":2,"output":12,"cacheRead":0.2,"official":true},"cheapest":{"provider":"google","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":4.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/google/deep-research-preview-04-2026/"},{"id":"google/gemini-robotics-er-1.6-preview","name":"Gemini Robotics-ER 1.6 Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"google","input":1,"output":5,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":1,"output":5,"cacheRead":null},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-14","lastUpdated":"2026-04-14","url":"https://llmpricing.dev/m/google/gemini-robotics-er-1.6-preview/"},{"id":"google/gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview 10-2025","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[128000,131072],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"google","input":1.25,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":1.25,"output":10,"cacheRead":null},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":3.4375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-07","lastUpdated":"2025-10-07","url":"https://llmpricing.dev/m/google/gemini-2.5-computer-use-preview-10-2025/"},{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"google","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":4,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-25","lastUpdated":"2026-03-25","url":"https://llmpricing.dev/m/google/lyria-3-clip-preview/"},{"id":"google/veo-3.1-fast-generate-preview","name":"Veo 3.1 fast","lab":"google","kind":"video","status":"ga","openWeights":false,"context":480,"contextRange":[480,400000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/google/veo-3.1-fast-generate-preview/"},{"id":"google/gemini-2.5-pro-preview-tts","name":"Gemini 2.5 Pro Preview TTS","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google","input":1,"output":20,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":1,"output":20,"cacheRead":null},"blendedRef":5.75,"blendedMin":5.75,"blendedTrusted":5.75,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-01","lastUpdated":"2025-05-01","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-preview-tts/"},{"id":"google/gemini-3.5-live-translate-preview","name":"Gemini 3.5 Live Translate Preview","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"google","input":3.5,"output":21,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":3.5,"output":21,"cacheRead":null},"blendedRef":7.875,"blendedMin":7.875,"blendedTrusted":7.875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/google/gemini-3.5-live-translate-preview/"},{"id":"google/veo-3.1-lite-generate-preview","name":"Veo 3.1 lite","lab":"google","kind":"video","status":"ga","openWeights":false,"context":480,"contextRange":[480,400000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-31","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/google/veo-3.1-lite-generate-preview/"},{"id":"google/gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[131072,1000000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"google","input":1.5,"output":17.5,"cacheRead":null,"official":true},"cheapest":{"provider":"vercel","input":1.5,"output":9,"cacheRead":null},"blendedRef":5.5,"blendedMin":3.375,"blendedTrusted":3.375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/google/gemini-omni-flash-preview/"},{"id":"google/gemini-2.5-flash-preview-tts","name":"Gemini 2.5 Flash Preview TTS","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"google","input":0.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":0.5,"output":10,"cacheRead":null},"blendedRef":2.875,"blendedMin":2.875,"blendedTrusted":2.875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-01","lastUpdated":"2025-05-01","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-tts/"},{"id":"google/veo-3.1-generate-preview","name":"Veo 3.1","lab":"google","kind":"video","status":"beta","openWeights":false,"context":480,"contextRange":[480,400000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":4,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/google/veo-3.1-generate-preview/"},{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","lab":"google","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"google","input":0.2,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":0.2,"output":0,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":null,"hostCount":3,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/google/gemini-embedding-2/"},{"id":"google/lyria-3-pro-preview","name":"Lyria 3 Pro Preview","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"google","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-25","lastUpdated":"2026-03-25","url":"https://llmpricing.dev/m/google/lyria-3-pro-preview/"},{"id":"google/deep-research-max-preview-04-2026","name":"Deep Research Max Preview (Apr-21-2026)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"google","input":2,"output":12,"cacheRead":0.2,"official":true},"cheapest":{"provider":"google","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":4.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/google/deep-research-max-preview-04-2026/"},{"id":"google/gemini-3.1-flash-live-preview","name":"Gemini 3.1 Flash Live Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"google","input":0.75,"output":4.5,"cacheRead":null,"official":true},"cheapest":{"provider":"google","input":0.75,"output":4.5,"cacheRead":null},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":1.6875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-26","lastUpdated":"2026-03-26","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-live-preview/"},{"id":"misc/auto","name":"Auto","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":[32000,1000000],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"morph","input":0.85,"output":1.55,"cacheRead":null,"official":false},"cheapest":{"provider":"morph","input":0.85,"output":1.55,"cacheRead":null},"blendedRef":1.025,"blendedMin":1.025,"blendedTrusted":null,"spread":null,"hostCount":4,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-29","lastUpdated":"2026-07-07","url":"https://llmpricing.dev/m/misc/auto/"},{"id":"openai/o4-mini-2","name":"o4-mini","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.1,"output":4.4,"cacheRead":0.275,"official":true},"cheapest":{"provider":"poe","input":0.99,"output":4,"cacheRead":0.25},"blendedRef":1.925,"blendedMin":1.7425,"blendedTrusted":1.925,"spread":1.1,"hostCount":17,"pricedHostCount":15,"aa":{"idx":26.1,"coding":null,"agentic":null,"speed":143,"ttft":29.16,"taskCost":null},"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-2/"},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","lab":"nvidia","kind":"text","status":"deprecated","openWeights":true,"context":256000,"contextRange":[131072,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"crusoe","input":0.3,"output":1.83,"cacheRead":0.3,"official":false},"cheapest":{"provider":"deepinfra","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.6825,"blendedMin":0.35,"blendedTrusted":0.35,"spread":1.5,"hostCount":3,"pricedHostCount":2,"aa":{"idx":15,"coding":13.8,"agentic":null,"speed":323,"ttft":1.03,"taskCost":null},"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-28","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning/"},{"id":"google/gemma-4-E4B-it","name":"Gemma 4 E4B IT","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":[32768,131072],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"pioneer","input":0.2,"output":0.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"deepinfra","input":0.02,"output":0.1,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.04,"blendedTrusted":0.04,"spread":10,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-E4B-it/"},{"id":"bytedance-seed/seed-2.0-code-2","name":"Seed 2.0 Code","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,262144],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"ofox","input":0.67,"output":3.36,"cacheRead":0.14,"official":false},"cheapest":{"provider":"merge-gateway","input":0.4,"output":2.4,"cacheRead":null},"blendedRef":1.3425,"blendedMin":0.9,"blendedTrusted":1.125,"spread":1.7,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.0-code-2/"},{"id":"bytedance-seed/seed-2.0-pro","name":"Seed 2.0 Pro","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[131072,256000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"empiriolabs","input":0.63,"output":3.79,"cacheRead":0.63,"official":false},"cheapest":{"provider":"requesty","input":0.45,"output":2.7,"cacheRead":0.09},"blendedRef":1.42,"blendedMin":1.0125,"blendedTrusted":1.125,"spread":1.5,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.0-pro/"},{"id":"bytedance-seed/seed-2.0-mini","name":"Seed 2.0 Mini","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[131072,262144],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"empiriolabs","input":0.12,"output":0.5,"cacheRead":0.12,"official":false},"cheapest":{"provider":"requesty","input":0.09,"output":0.36,"cacheRead":0.018},"blendedRef":0.215,"blendedMin":0.1575,"blendedTrusted":0.175,"spread":2,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.0-mini/"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct-turbo","name":"Qwen3 Coder 480B A35B Instruct Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":66536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"deepinfra","input":0.3,"output":1,"cacheRead":0.1,"official":false},"cheapest":{"provider":"helicone","input":0.22,"output":0.95,"cacheRead":null},"blendedRef":0.475,"blendedMin":0.4025,"blendedTrusted":0.475,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-480b-a35b-instruct-turbo/"},{"id":"meta/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B FP8","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"deepinfra","input":0.2,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"deepinfra","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":0.35,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-128e-instruct-fp8/"},{"id":"meta/llama-3.3-70b-instruct-turbo","name":"Llama 3.3 70B Turbo","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"deepinfra","input":0.1,"output":0.32,"cacheRead":null,"official":false},"cheapest":{"provider":"deepinfra","input":0.1,"output":0.32,"cacheRead":null},"blendedRef":0.155,"blendedMin":0.155,"blendedTrusted":0.155,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct-turbo/"},{"id":"meta/llama-4-scout-17b-16e-instruct-2","name":"Llama 4 Scout 17B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":327680,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"deepinfra","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"deepinfra","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-16e-instruct-2/"},{"id":"meta/muse-spark-1.2-contributor-2","name":"Muse Spark 1.2 Contributor","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":{"provider":"meta","input":0.1,"output":0.2,"cacheRead":0.002,"official":true},"cheapest":{"provider":"meta","input":0.1,"output":0.2,"cacheRead":0.002},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":0.125,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-08-05","lastUpdated":"2026-08-05","url":"https://llmpricing.dev/m/meta/muse-spark-1.2-contributor-2/"},{"id":"moonshotai/kimi-k2-instruct-0905","name":"Kimi-K2-Instruct-0905","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"huggingface","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"huggingface","input":1,"output":3,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":1.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-04","lastUpdated":"2025-09-04","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-instruct-0905/"},{"id":"alibaba/qwen3-embedding-8b","name":"Qwen3-Embedding-8B","lab":"alibaba","kind":"embedding","status":"ga","openWeights":true,"context":40960,"contextRange":[32000,40960],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"evroc","input":0.115,"output":0.115,"cacheRead":null,"official":false},"cheapest":{"provider":"huggingface","input":0.01,"output":0,"cacheRead":null},"blendedRef":0.115,"blendedMin":0.0075,"blendedTrusted":0.0075,"spread":11.5,"hostCount":7,"pricedHostCount":5,"aa":null,"usage":{"rank":58,"tokens":231675399587,"share":0.000868216824386298},"releaseDate":"2025-06-05","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/alibaba/qwen3-embedding-8b/"},{"id":"alibaba/qwen3-embedding-4b","name":"Qwen 3 Embedding 4B","lab":"alibaba","kind":"embedding","status":"ga","openWeights":true,"context":32000,"contextRange":[32000,32768],"outputLimit":2560,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"privatemode-ai","input":0.1502,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"huggingface","input":0.01,"output":0,"cacheRead":null},"blendedRef":0.1127,"blendedMin":0.0075,"blendedTrusted":0.0075,"spread":15,"hostCount":4,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-06-06","url":"https://llmpricing.dev/m/alibaba/qwen3-embedding-4b/"},{"id":"openai/o1-2","name":"o1","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":15,"output":60,"cacheRead":7.5,"official":true},"cheapest":{"provider":"poe","input":14,"output":54,"cacheRead":null},"blendedRef":26.25,"blendedMin":24,"blendedTrusted":26.25,"spread":1.1,"hostCount":12,"pricedHostCount":12,"aa":{"idx":23.9,"coding":39.7,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-12-05","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/openai/o1-2/"},{"id":"openai/o3-2","name":"o3","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[131072,200000],"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":2,"output":8,"cacheRead":0.5,"official":true},"cheapest":{"provider":"poe","input":1.8,"output":7.2,"cacheRead":0.45},"blendedRef":3.5,"blendedMin":3.15,"blendedTrusted":3.5,"spread":5.6,"hostCount":16,"pricedHostCount":15,"aa":{"idx":31.1,"coding":null,"agentic":null,"speed":112,"ttft":8.31,"taskCost":null},"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o3-2/"},{"id":"openai/o3-mini-2","name":"o3-mini","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":[131072,200000],"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.1,"output":4.4,"cacheRead":0.55,"official":true},"cheapest":{"provider":"poe","input":0.99,"output":4,"cacheRead":null},"blendedRef":1.925,"blendedMin":1.7425,"blendedTrusted":1.925,"spread":1.1,"hostCount":16,"pricedHostCount":15,"aa":{"idx":19.2,"coding":null,"agentic":null,"speed":221,"ttft":6.45,"taskCost":null},"usage":null,"releaseDate":"2024-12-20","lastUpdated":"2025-01-29","url":"https://llmpricing.dev/m/openai/o3-mini-2/"},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","lab":"xai","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":[262000,2000000],"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"xai","input":1.25,"output":2.5,"cacheRead":0.2,"official":true},"cheapest":{"provider":"impossibl","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":1.5625,"spread":1.6,"hostCount":8,"pricedHostCount":8,"aa":{"idx":22.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/xai/grok-4.20-0309-non-reasoning/"},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","lab":"xai","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":[262000,2000000],"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"xai","input":1.25,"output":2.5,"cacheRead":0.2,"official":true},"cheapest":{"provider":"impossibl","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":1.5625,"spread":3.2,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/xai/grok-4.20-0309-reasoning/"},{"id":"google/gemini-2.5-flash-lite-preview-06-17-2","name":"gemini-2.5-flash-lite-preview-06-17","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","video","image","audio"],"reference":{"provider":"jiekou","input":0.09,"output":0.36,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.09,"output":0.36,"cacheRead":null},"blendedRef":0.1575,"blendedMin":0.1575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-preview-06-17-2/"},{"id":"anthropic/claude-opus-4-20250514-3","name":"claude-opus-4-20250514","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":15,"output":75,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":13.5,"output":67.5,"cacheRead":null},"blendedRef":30,"blendedMin":27,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-20250514-3/"},{"id":"xai/grok-4-fast-reasoning-2","name":"grok-4-fast-reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":0.2,"output":0.5,"cacheRead":0.05,"official":false},"cheapest":{"provider":"jiekou","input":0.18,"output":0.45,"cacheRead":null},"blendedRef":0.275,"blendedMin":0.2475,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xai/grok-4-fast-reasoning-2/"},{"id":"anthropic/claude-opus-4-1-20250805-2","name":"claude-opus-4-1-20250805","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":15,"output":75,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":13.5,"output":67.5,"cacheRead":null},"blendedRef":30,"blendedMin":27,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-20250805-2/"},{"id":"google/gemini-2.5-flash-preview-05-20-2","name":"gemini-2.5-flash-preview-05-20","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":200000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"jiekou","input":0.135,"output":3.15,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.135,"output":3.15,"cacheRead":null},"blendedRef":0.8888,"blendedMin":0.8888,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-preview-05-20-2/"},{"id":"xai/grok-code-fast-1-2","name":"Grok Code Fast 1","lab":"xai","kind":"text","status":"deprecated","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"abacus","input":0.2,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.18,"output":1.35,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.4725,"blendedTrusted":null,"spread":1.1,"hostCount":5,"pricedHostCount":4,"aa":{"idx":22,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xai/grok-code-fast-1-2/"},{"id":"xai/grok-4-1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","lab":"xai","kind":"text","status":"beta","openWeights":false,"context":256000,"contextRange":[128000,2000000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"frogbot","input":0.2,"output":1.5,"cacheRead":0.02,"official":false},"cheapest":{"provider":"jiekou","input":0.18,"output":0.45,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.2475,"blendedTrusted":0.275,"spread":1.1,"hostCount":8,"pricedHostCount":7,"aa":null,"usage":null,"releaseDate":"2025-11-19","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xai/grok-4-1-fast-reasoning/"},{"id":"anthropic/claude-sonnet-4-5-20250929-2","name":"claude-sonnet-4-5-20250929","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":2.7,"output":13.5,"cacheRead":null},"blendedRef":6,"blendedMin":5.4,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-20250929-2/"},{"id":"xai/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","lab":"xai","kind":"text","status":"deprecated","openWeights":false,"context":2000000,"contextRange":[128000,2000000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":0.2,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.18,"output":0.45,"cacheRead":null},"blendedRef":0.275,"blendedMin":0.2475,"blendedTrusted":0.275,"spread":1.1,"hostCount":10,"pricedHostCount":9,"aa":null,"usage":null,"releaseDate":"2025-11-19","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xai/grok-4-1-fast-non-reasoning/"},{"id":"anthropic/claude-haiku-4-5-20251001-2","name":"claude-haiku-4-5-20251001","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[20000,200000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":1,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.9,"output":4.5,"cacheRead":null},"blendedRef":2,"blendedMin":1.8,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-20251001-2/"},{"id":"xai/grok-4-fast-non-reasoning-2","name":"grok-4-fast-non-reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"abacus","input":0.2,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.18,"output":0.45,"cacheRead":null},"blendedRef":0.275,"blendedMin":0.2475,"blendedTrusted":null,"spread":1.1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xai/grok-4-fast-non-reasoning-2/"},{"id":"anthropic/claude-opus-4-5-20251101-2","name":"claude-opus-4-5-20251101","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":5,"output":25,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":4.5,"output":22.5,"cacheRead":null},"blendedRef":10,"blendedMin":9,"blendedTrusted":null,"spread":1.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-20251101-2/"},{"id":"xai/grok-4-0709","name":"grok-4-0709","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"jiekou","input":2.7,"output":13.5,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":2.7,"output":13.5,"cacheRead":null},"blendedRef":5.4,"blendedMin":5.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xai/grok-4-0709/"},{"id":"anthropic/claude-sonnet-4-20250514-3","name":"claude-sonnet-4-20250514","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":2.7,"output":13.5,"cacheRead":null},"blendedRef":6,"blendedMin":5.4,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-20250514-3/"},{"id":"alibaba/qwen3-coder-next-2","name":"qwen/qwen3-coder-next","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"jiekou","input":0.2,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.2,"output":1.5,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02","lastUpdated":"2026-02","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-next-2/"},{"id":"xiaomi/mimo-v2-flash-3","name":"XiaomiMiMo/MiMo-V2-Flash","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.1,"output":0.3,"cacheRead":0.3,"official":false},"cheapest":{"provider":"novita-ai","input":0.1,"output":0.3,"cacheRead":0.3},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-flash-3/"},{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","lab":"baidu","kind":"text","status":"ga","openWeights":true,"context":123000,"contextRange":null,"outputLimit":123000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.42,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.42,"output":1.25,"cacheRead":null},"blendedRef":0.6275,"blendedMin":0.6275,"blendedTrusted":null,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/baidu/ernie-4.5-vl-424b-a47b/"},{"id":"baidu/ernie-4.5-300b-a47b-paddle","name":"ERNIE 4.5 300B A47B","lab":"baidu","kind":"text","status":"ga","openWeights":true,"context":123000,"contextRange":null,"outputLimit":12000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.28,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"jiekou","input":0.28,"output":1.1,"cacheRead":null},"blendedRef":0.485,"blendedMin":0.485,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":8.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/baidu/ernie-4.5-300b-a47b-paddle/"},{"id":"misc/mercury-edit-2","name":"Mercury Edit 2","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"inception","input":0.25,"output":0.75,"cacheRead":0.025,"official":false},"cheapest":{"provider":"inception","input":0.25,"output":0.75,"cacheRead":0.025},"blendedRef":0.375,"blendedMin":0.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-30","lastUpdated":"2026-03-30","url":"https://llmpricing.dev/m/misc/mercury-edit-2/"},{"id":"deepcogito/cogito-v2.1-671b","name":"Cogito v2.1 671B","lab":"deepcogito","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":[128000,163840],"outputLimit":163840,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":1.25,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":1.25,"output":1.25,"cacheRead":null},"blendedRef":1.25,"blendedMin":1.25,"blendedTrusted":1.25,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/deepcogito/cogito-v2.1-671b/"},{"id":"tencent/hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.074,"output":0.295,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.074,"output":0.295,"cacheRead":null},"blendedRef":0.1292,"blendedMin":0.1292,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/tencent/hy-mt2-30b-a3b/"},{"id":"tencent/hy-mt2-1.8b","name":"Hy-MT2-1.8B","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.044,"output":0.177,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.044,"output":0.177,"cacheRead":null},"blendedRef":0.0773,"blendedMin":0.0773,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/tencent/hy-mt2-1.8b/"},{"id":"tencent/hunyuan-a13b-instruct","name":"Hunyuan A13B Instruct","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.14,"output":0.57,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.14,"output":0.57,"cacheRead":null},"blendedRef":0.2475,"blendedMin":0.2475,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-08","lastUpdated":"2025-07-08","url":"https://llmpricing.dev/m/tencent/hunyuan-a13b-instruct/"},{"id":"anthropic/claude-haiku-latest-2","name":"Anthropic Claude Haiku Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"openrouter","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/anthropic/claude-haiku-latest-2/"},{"id":"anthropic/claude-sonnet-latest-2","name":"Anthropic Claude Sonnet Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"openrouter","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-latest-2/"},{"id":"nvidia/nemotron-3-super-120b-a12b-free","name":"Nemotron 3 Super (free)","lab":"nvidia","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[204800,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":{"rank":28,"tokens":1529645684048,"share":0.005732434779902643},"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b-free/"},{"id":"nvidia/nemotron-nano-12b-v2-vl-free","name":"Nemotron Nano 12B 2 VL (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-28","lastUpdated":"2025-10-28","url":"https://llmpricing.dev/m/nvidia/nemotron-nano-12b-v2-vl-free/"},{"id":"nvidia/nemotron-3.5-lightning-free","name":"Nemotron 3.5 Lightning (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[262144,1000000],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":{"rank":33,"tokens":1109140462333,"share":0.004156567385755113},"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-lightning-free/"},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-free","name":"Nemotron 3 Nano Omni (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-28","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-free/"},{"id":"nvidia/nemotron-3.5-content-safety-free","name":"Nemotron 3.5 Content Safety (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-content-safety-free/"},{"id":"nvidia/nemotron-3-ultra-550b-a55b-free","name":"Nemotron 3 Ultra (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":{"rank":8,"tokens":11338369728081,"share":0.04249118972744228},"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-a55b-free/"},{"id":"nvidia/nemotron-3-nano-30b-a3b-free","name":"Nemotron 3 Nano 30B A3B (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2025-12-15","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-30b-a3b-free/"},{"id":"nvidia/nemotron-nano-9b-v2-free","name":"Nemotron Nano 9B V2 (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-18","lastUpdated":"2025-08-18","url":"https://llmpricing.dev/m/nvidia/nemotron-nano-9b-v2-free/"},{"id":"openai/gpt-latest-2","name":"OpenAI GPT Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["pdf","image","text"],"reference":{"provider":"kilo","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"openrouter","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/openai/gpt-latest-2/"},{"id":"openai/gpt-mini-latest","name":"OpenAI GPT Mini Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["pdf","image","text"],"reference":{"provider":"kilo","input":0.75,"output":4.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"openrouter","input":0.75,"output":4.5,"cacheRead":0.075},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/openai/gpt-mini-latest/"},{"id":"aion-labs/aion-3.0-2","name":"Aion-3.0","lab":"aion-labs","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,131072],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":3.75,"output":7.5,"cacheRead":0.9375,"official":false},"cheapest":{"provider":"openrouter","input":3,"output":6,"cacheRead":0.75},"blendedRef":4.6875,"blendedMin":3.75,"blendedTrusted":null,"spread":1.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-07","lastUpdated":"2026-07-08","url":"https://llmpricing.dev/m/aion-labs/aion-3.0-2/"},{"id":"meta/aion-rp-llama-3.1-8b-2","name":"Aion-RP 1.0 (8B)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.8,"output":1.6,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.8,"output":1.6,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-04","lastUpdated":"2025-02-04","url":"https://llmpricing.dev/m/meta/aion-rp-llama-3.1-8b-2/"},{"id":"aion-labs/aion-2.0-2","name":"Aion-2.0","lab":"aion-labs","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.8,"output":1.6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"openrouter","input":0.8,"output":1.6,"cacheRead":0.2},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/aion-labs/aion-2.0-2/"},{"id":"aion-labs/aion-3.0-mini-2","name":"Aion-3.0-Mini","lab":"aion-labs","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,131072],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.875,"output":1.75,"cacheRead":0.225,"official":false},"cheapest":{"provider":"openrouter","input":0.7,"output":1.4,"cacheRead":0.18},"blendedRef":1.0938,"blendedMin":0.875,"blendedTrusted":null,"spread":1.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-07","lastUpdated":"2026-07-08","url":"https://llmpricing.dev/m/aion-labs/aion-3.0-mini-2/"},{"id":"microsoft/phi-4","name":"Phi-4","lab":"microsoft","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[16384,128000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure-cognitive-services","input":0.125,"output":0.5,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.07,"output":0.14,"cacheRead":null},"blendedRef":0.2188,"blendedMin":0.0875,"blendedTrusted":0.2188,"spread":1.8,"hostCount":3,"pricedHostCount":3,"aa":{"idx":4.6,"coding":null,"agentic":null,"speed":39,"ttft":2.59,"taskCost":null},"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2025-01-10","url":"https://llmpricing.dev/m/microsoft/phi-4/"},{"id":"zhipuai/glm-5.2-free","name":"GLM 5.2 (free)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,1000000],"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":{"rank":6,"tokens":15302816087671,"share":0.05734817944196953},"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-free/"},{"id":"zhipuai/glm-5.3-2","name":"GLM-5.3","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":1.75,"output":5.5,"cacheRead":0.325,"official":false},"cheapest":{"provider":"merge-gateway","input":0.7,"output":2.2,"cacheRead":0.13},"blendedRef":2.6875,"blendedMin":1.075,"blendedTrusted":2.15,"spread":2.5,"hostCount":15,"pricedHostCount":13,"aa":{"idx":59.5,"coding":74.8,"agentic":59.1,"speed":85,"ttft":1.88,"taskCost":0.6829},"usage":{"rank":59,"tokens":171244463841,"share":0.0006417484327417126},"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/zhipuai/glm-5.3-2/"},{"id":"deepseek/deepseek-r1-0528-2","name":"R1 0528","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.5,"output":2.15,"cacheRead":0.35,"official":false},"cheapest":{"provider":"openrouter","input":0.5,"output":2.15,"cacheRead":0.35},"blendedRef":0.9125,"blendedMin":0.9125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-28","lastUpdated":"2025-05-28","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-0528-2/"},{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"R1 Distill Llama 70B","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.8,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.8,"output":0.8,"cacheRead":null},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-23","lastUpdated":"2025-01-23","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-distill-llama-70b/"},{"id":"arcee-ai/virtuoso-large","name":"Virtuoso Large","lab":"arcee-ai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.75,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.75,"output":1.2,"cacheRead":null},"blendedRef":0.8625,"blendedMin":0.8625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-05","lastUpdated":"2025-05-05","url":"https://llmpricing.dev/m/arcee-ai/virtuoso-large/"},{"id":"google/gemma-2-27b-it","name":"Gemma 2 27B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.65,"output":0.65,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.65,"output":0.65,"cacheRead":null},"blendedRef":0.65,"blendedMin":0.65,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-13","lastUpdated":"2024-07-13","url":"https://llmpricing.dev/m/google/gemma-2-27b-it/"},{"id":"google/gemma-3-4b-it-2","name":"Gemma 3 4B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.05,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.05,"output":0.1,"cacheRead":null},"blendedRef":0.0625,"blendedMin":0.0625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":1,"coding":2.7,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/google/gemma-3-4b-it-2/"},{"id":"google/gemma-3n-e4b-it-2","name":"Gemma 3n 4B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.06,"output":0.12,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.06,"output":0.12,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/google/gemma-3n-e4b-it-2/"},{"id":"google/gemma-4-31b-it-free","name":"Gemma 4 31B (free)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["image","text","video"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":{"rank":26,"tokens":1815745283678,"share":0.006804609409974537},"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-free/"},{"id":"google/gemma-3-12b-it-2","name":"Gemma 3 12B","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"neon","input":0.15,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.05,"output":0.1,"cacheRead":null},"blendedRef":0.2375,"blendedMin":0.0625,"blendedTrusted":0.2375,"spread":3,"hostCount":3,"pricedHostCount":3,"aa":{"idx":5.5,"coding":5.8,"agentic":0.3,"speed":null,"ttft":null,"taskCost":0},"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/google/gemma-3-12b-it-2/"},{"id":"google/gemma-4-26b-a4b-it-free","name":"Gemma 4 26B A4B  (free)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["image","text","video"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":{"rank":29,"tokens":1517861731252,"share":0.005688273742116587},"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-it-free/"},{"id":"mistral/dolphin-mistral-24b-venice-edition","name":"Uncensored","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.2,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.2,"output":0.9,"cacheRead":null},"blendedRef":0.375,"blendedMin":0.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/mistral/dolphin-mistral-24b-venice-edition/"},{"id":"misc/auto-2","name":"Auto Router","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-11-08","lastUpdated":"2026-03-15","url":"https://llmpricing.dev/m/misc/auto-2/"},{"id":"misc/bodybuilder","name":"Body Builder (beta)","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-05","lastUpdated":"2026-03-15","url":"https://llmpricing.dev/m/misc/bodybuilder/"},{"id":"misc/fusion","name":"Fusion","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/misc/fusion/"},{"id":"misc/pareto-code","name":"Pareto Code Router","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":[200000,2000000],"outputLimit":200000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-05-01","url":"https://llmpricing.dev/m/misc/pareto-code/"},{"id":"misc/free","name":"Free Models Router","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-02-01","url":"https://llmpricing.dev/m/misc/free/"},{"id":"poolside/laguna-xs-2.1-free","name":"Laguna XS 2.1 (free)","lab":"poolside","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":{"rank":50,"tokens":475787269113,"share":0.0017830400319115167},"releaseDate":"2026-07-02","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/poolside/laguna-xs-2.1-free/"},{"id":"poolside/laguna-s-2.1-free","name":"Laguna S 2.1 Free","lab":"poolside","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":3,"pricedHostCount":0,"aa":null,"usage":{"rank":14,"tokens":5656207025011,"share":0.021196959668919813},"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/poolside/laguna-s-2.1-free/"},{"id":"bytedance-seed/seed-1-6-flash","name":"Seed 1.6 Flash","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["image","text","video"],"reference":{"provider":"openrouter","input":0.075,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"ofox","input":0.03,"output":0.22,"cacheRead":0.0043},"blendedRef":0.1312,"blendedMin":0.0775,"blendedTrusted":null,"spread":2.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-08-28","lastUpdated":"2025-08-28","url":"https://llmpricing.dev/m/bytedance-seed/seed-1-6-flash/"},{"id":"bytedance-seed/seed-1-6","name":"Seed 1.6","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,262144],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["image","text","video"],"reference":{"provider":"vercel","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"ofox","input":0.12,"output":0.29,"cacheRead":0.023},"blendedRef":0.6875,"blendedMin":0.1625,"blendedTrusted":0.6875,"spread":2.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/bytedance-seed/seed-1-6/"},{"id":"bytedance-seed/seed-2.0-lite-2","name":"Seed 2.0 Lite","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[131072,262144],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"empiriolabs","input":0.31,"output":2.5,"cacheRead":0.31,"official":false},"cheapest":{"provider":"ofox","input":0.13,"output":0.76,"cacheRead":0.03},"blendedRef":0.8575,"blendedMin":0.2875,"blendedTrusted":null,"spread":2.4,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-02-14","lastUpdated":"2026-02-14","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.0-lite-2/"},{"id":"bytedance-seed/seed-2.1-turbo","name":"Seed 2.1 Turbo","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"empiriolabs","input":0.63,"output":3.13,"cacheRead":0.63,"official":false},"cheapest":{"provider":"ofox","input":0.3536,"output":1.7696,"cacheRead":0.068},"blendedRef":1.255,"blendedMin":0.7076,"blendedTrusted":null,"spread":1.8,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.1-turbo/"},{"id":"anthropic/claude-3-haiku","name":"Claude 3 Haiku","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.25,"output":1.25,"cacheRead":0.03,"official":false},"cheapest":{"provider":"openrouter","input":0.25,"output":1.25,"cacheRead":0.03},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":3.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-03-13","lastUpdated":"2024-03-13","url":"https://llmpricing.dev/m/anthropic/claude-3-haiku/"},{"id":"anthropic/claude-opus-4.7-fast","name":"Claude Opus 4.7 (Fast)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openrouter","input":30,"output":150,"cacheRead":3,"official":false},"cheapest":{"provider":"openrouter","input":30,"output":150,"cacheRead":3},"blendedRef":60,"blendedMin":60,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.7-fast/"},{"id":"anthropic/claude-opus-4.8-fast","name":"Claude Opus 4.8 (Fast)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"venice","input":12,"output":60,"cacheRead":1.2,"official":false},"cheapest":{"provider":"openrouter","input":10,"output":50,"cacheRead":1},"blendedRef":24,"blendedMin":20,"blendedTrusted":20,"spread":1.2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.8-fast/"},{"id":"anthropic/claude-opus-5-fast","name":"Claude Opus 5 (Fast)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"venice","input":12,"output":60,"cacheRead":1.2,"official":false},"cheapest":{"provider":"openrouter","input":10,"output":50,"cacheRead":1},"blendedRef":24,"blendedMin":20,"blendedTrusted":20,"spread":1.2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/claude-opus-5-fast/"},{"id":"cohere/command-r-plus-08-2024-2","name":"Command R+","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":4.375,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":16.7,"hostCount":9,"pricedHostCount":8,"aa":{"idx":2.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-08-30","lastUpdated":"2024-08-30","url":"https://llmpricing.dev/m/cohere/command-r-plus-08-2024-2/"},{"id":"cohere/command-a-03-2025","name":"Command A","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[131072,288000],"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":1,"hostCount":6,"pricedHostCount":6,"aa":{"idx":22.8,"coding":27.8,"agentic":9.2,"speed":207,"ttft":0.38,"taskCost":0},"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/cohere/command-a-03-2025/"},{"id":"cohere/north-mini-code-free","name":"North Mini Code (free)","lab":"cohere","kind":"text","status":"deprecated","openWeights":true,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":{"rank":35,"tokens":1029847371496,"share":0.003859411987965794},"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/cohere/north-mini-code-free/"},{"id":"cohere/command-r7b-12-2024","name":"Command R7B","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,132000],"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":0.0375,"output":0.15,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.0375,"output":0.15,"cacheRead":null},"blendedRef":0.0656,"blendedMin":0.0656,"blendedTrusted":0.0656,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-12-02","lastUpdated":"2024-12-02","url":"https://llmpricing.dev/m/cohere/command-r7b-12-2024/"},{"id":"bytedance/ui-tars-1.5-7b","name":"UI-TARS 7B ","lab":"bytedance","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"openrouter","input":0.1,"output":0.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"openrouter","input":0.1,"output":0.2,"cacheRead":0.1},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-22","lastUpdated":"2025-07-22","url":"https://llmpricing.dev/m/bytedance/ui-tars-1.5-7b/"},{"id":"google/gemini-flash-latest-2","name":"Google Gemini Flash Latest","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":{"provider":"kilo","input":0.375,"output":1.875,"cacheRead":0.0375,"official":false},"cheapest":{"provider":"openrouter","input":0.375,"output":1.875,"cacheRead":0.0375},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/google/gemini-flash-latest-2/"},{"id":"google/gemini-pro-latest-2","name":"Google Gemini Pro Latest","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["audio","pdf","image","text","video"],"reference":{"provider":"kilo","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"openrouter","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/google/gemini-pro-latest-2/"},{"id":"openai/gpt-audio","name":"GPT Audio","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"openrouter","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/openai/gpt-audio/"},{"id":"openai/gpt-3.5-turbo-16k","name":"GPT-3.5 Turbo 16k","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":16385,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":3,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":3,"output":4,"cacheRead":null},"blendedRef":3.25,"blendedMin":3.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-08-28","lastUpdated":"2023-08-28","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-16k/"},{"id":"openai/o1-pro-2","name":"o1-pro","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":150,"output":600,"cacheRead":null,"official":true},"cheapest":{"provider":"poe","input":140,"output":540,"cacheRead":null},"blendedRef":262.5,"blendedMin":240,"blendedTrusted":262.5,"spread":1.1,"hostCount":6,"pricedHostCount":6,"aa":{"idx":19.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-03-19","lastUpdated":"2025-03-19","url":"https://llmpricing.dev/m/openai/o1-pro-2/"},{"id":"openai/gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":4096,"contextRange":[3500,4096],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"azure","input":1.5,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":1.4,"output":1.8,"cacheRead":null},"blendedRef":1.625,"blendedMin":1.5,"blendedTrusted":1.625,"spread":1.1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2023-09-21","lastUpdated":"2023-09-28","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-instruct/"},{"id":"openai/o3-pro","name":"o3-pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf","image"],"reference":{"provider":"openai","input":20,"output":80,"cacheRead":null,"official":true},"cheapest":{"provider":"abacus","input":20,"output":40,"cacheRead":null},"blendedRef":35,"blendedMin":25,"blendedTrusted":35,"spread":1.1,"hostCount":8,"pricedHostCount":8,"aa":{"idx":33.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-06-10","lastUpdated":"2025-06-10","url":"https://llmpricing.dev/m/openai/o3-pro/"},{"id":"openai/gpt-4o-mini-2024-07-18","name":"GPT-4o-mini (2024-07-18)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openrouter","input":0.15,"output":0.6,"cacheRead":0.075,"official":false},"cheapest":{"provider":"openrouter","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-2024-07-18/"},{"id":"openai/o4-mini-high-2","name":"o4 Mini High","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text","pdf"],"reference":{"provider":"openrouter","input":1.1,"output":4.4,"cacheRead":0.275,"official":false},"cheapest":{"provider":"openrouter","input":1.1,"output":4.4,"cacheRead":0.275},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-high-2/"},{"id":"openai/gpt-oss-20b-free","name":"gpt-oss-20b (free)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":{"rank":57,"tokens":280573533627,"share":0.0010514653813341053},"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-20b-free/"},{"id":"openai/gpt-5-image-mini","name":"GPT-5 Image Mini","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["pdf","image","text"],"reference":{"provider":"openrouter","input":2.5,"output":2,"cacheRead":0.25,"official":false},"cheapest":{"provider":"openrouter","input":2.5,"output":2,"cacheRead":0.25},"blendedRef":2.375,"blendedMin":2.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-16","lastUpdated":"2025-10-16","url":"https://llmpricing.dev/m/openai/gpt-5-image-mini/"},{"id":"openai/gpt-5.4-image-2","name":"GPT-5.4 Image 2","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":272000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["image","text","pdf"],"reference":{"provider":"openrouter","input":8,"output":15,"cacheRead":2,"official":false},"cheapest":{"provider":"openrouter","input":8,"output":15,"cacheRead":2},"blendedRef":9.75,"blendedMin":9.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/openai/gpt-5.4-image-2/"},{"id":"openai/gpt-audio-mini","name":"GPT Audio Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"openrouter","input":0.6,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.6,"output":2.4,"cacheRead":null},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/openai/gpt-audio-mini/"},{"id":"openai/o3-mini-high-2","name":"o3 Mini High","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf","image"],"reference":{"provider":"openrouter","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"poe","input":0.99,"output":4,"cacheRead":null},"blendedRef":1.925,"blendedMin":1.7425,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-02-12","lastUpdated":"2025-02-12","url":"https://llmpricing.dev/m/openai/o3-mini-high-2/"},{"id":"openai/gpt-3.5-turbo-0613","name":"GPT-3.5 Turbo (older v0613)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":4095,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":1,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":1,"output":2,"cacheRead":null},"blendedRef":1.25,"blendedMin":1.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-0613/"},{"id":"openai/gpt-5-image","name":"GPT-5 Image","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["image","text","pdf"],"reference":{"provider":"openrouter","input":10,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"openrouter","input":10,"output":10,"cacheRead":1.25},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-14","lastUpdated":"2025-10-14","url":"https://llmpricing.dev/m/openai/gpt-5-image/"},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Hermes 3 405B Instruct","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":1,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":1,"output":1,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-16","lastUpdated":"2024-08-16","url":"https://llmpricing.dev/m/nousresearch/hermes-3-llama-3.1-405b/"},{"id":"nousresearch/hermes-3-llama-3.1-70b-2","name":"Hermes 3 70B Instruct","lab":"nousresearch","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.7,"output":0.7,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.7,"output":0.7,"cacheRead":null},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-18","lastUpdated":"2024-08-18","url":"https://llmpricing.dev/m/nousresearch/hermes-3-llama-3.1-70b-2/"},{"id":"alibaba/qwen3.5-plus-20260420","name":"Qwen3.5 Plus 2026-04-20","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"openrouter","input":0.3,"output":1.8,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.3,"output":1.8,"cacheRead":null},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/alibaba/qwen3.5-plus-20260420/"},{"id":"alibaba/qwen-plus-2025-07-28-thinking","name":"Qwen Plus 0728 (thinking)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.26,"output":0.78,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.26,"output":0.78,"cacheRead":null},"blendedRef":0.39,"blendedMin":0.39,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-08","lastUpdated":"2025-09-08","url":"https://llmpricing.dev/m/alibaba/qwen-plus-2025-07-28-thinking/"},{"id":"alibaba/qwen3-vl-8b-thinking","name":"Qwen3 VL 8B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"openrouter","input":0.18,"output":2.1,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.18,"output":2.1,"cacheRead":null},"blendedRef":0.66,"blendedMin":0.66,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-14","lastUpdated":"2025-10-14","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-8b-thinking/"},{"id":"alibaba/qwen3.5-plus-02-15","name":"Qwen3.5 Plus 2026-02-15","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"openrouter","input":0.26,"output":1.56,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.26,"output":1.56,"cacheRead":null},"blendedRef":0.585,"blendedMin":0.585,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-plus-02-15/"},{"id":"alibaba/qwen3-coder-2","name":"Qwen3 Coder 480B A35B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":1,"output":1.5,"cacheRead":1,"official":false},"cheapest":{"provider":"openrouter","input":0.3,"output":1,"cacheRead":0.1},"blendedRef":1.125,"blendedMin":0.475,"blendedTrusted":1.125,"spread":3.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-2/"},{"id":"alibaba/qwen2-5-7b-instruct","name":"Qwen2.5 7B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.072,"output":0.144,"cacheRead":null,"official":true},"cheapest":{"provider":"novita-ai","input":0.07,"output":0.07,"cacheRead":null},"blendedRef":0.09,"blendedMin":0.07,"blendedTrusted":0.09,"spread":2.5,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/alibaba/qwen2-5-7b-instruct/"},{"id":"alibaba/qwen3-max-thinking","name":"Qwen3 Max Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":1.2,"output":6,"cacheRead":0.24,"official":false},"cheapest":{"provider":"openrouter","input":0.78,"output":3.9,"cacheRead":null},"blendedRef":2.4,"blendedMin":1.56,"blendedTrusted":2.4,"spread":1.5,"hostCount":3,"pricedHostCount":3,"aa":{"idx":32.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-01-23","lastUpdated":"2026-02-09","url":"https://llmpricing.dev/m/alibaba/qwen3-max-thinking/"},{"id":"alibaba/qwen3-vl-8b-instruct","name":"Qwen3 VL 8B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"openrouter","input":0.117,"output":0.455,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.117,"output":0.455,"cacheRead":null},"blendedRef":0.2015,"blendedMin":0.2015,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":8.2,"coding":null,"agentic":null,"speed":107,"ttft":2.26,"taskCost":null},"usage":null,"releaseDate":"2025-10-14","lastUpdated":"2025-10-14","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-8b-instruct/"},{"id":"alibaba/qwen-plus-2025-07-28","name":"Qwen Plus 0728","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.26,"output":0.78,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.26,"output":0.78,"cacheRead":null},"blendedRef":0.39,"blendedMin":0.39,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-08","lastUpdated":"2025-09-08","url":"https://llmpricing.dev/m/alibaba/qwen-plus-2025-07-28/"},{"id":"alibaba/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[256000,262144],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.13,"output":0.52,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2275,"blendedTrusted":null,"spread":1.2,"hostCount":3,"pricedHostCount":3,"aa":{"idx":9.9,"coding":null,"agentic":null,"speed":109,"ttft":2.14,"taskCost":null},"usage":null,"releaseDate":"2025-10-06","lastUpdated":"2025-10-06","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-30b-a3b-instruct/"},{"id":"alibaba/qwen-2.5-72b-instruct-2","name":"Qwen2.5 72B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[32000,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.574,"output":1.721,"cacheRead":null,"official":true},"cheapest":{"provider":"abacus","input":0.11,"output":0.38,"cacheRead":null},"blendedRef":0.8608,"blendedMin":0.1775,"blendedTrusted":0.8608,"spread":12.7,"hostCount":6,"pricedHostCount":6,"aa":{"idx":9.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-09-19","lastUpdated":"2024-10-15","url":"https://llmpricing.dev/m/alibaba/qwen-2.5-72b-instruct-2/"},{"id":"alibaba/qwen3-vl-32b-instruct","name":"Qwen3 VL 32B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.104,"output":0.416,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.104,"output":0.416,"cacheRead":null},"blendedRef":0.182,"blendedMin":0.182,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":11,"coding":null,"agentic":null,"speed":67,"ttft":2.53,"taskCost":null},"usage":null,"releaseDate":"2025-10-23","lastUpdated":"2025-10-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-32b-instruct/"},{"id":"liquid/lfm-2.5-2.6b-free","name":"LFM2.5-2.6B (free)","lab":"liquid","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/liquid/lfm-2.5-2.6b-free/"},{"id":"allenai/olmo-3-32b-think","name":"Olmo 3 32B Think","lab":"allenai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.15,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.15,"output":0.5,"cacheRead":null},"blendedRef":0.2375,"blendedMin":0.2375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":6.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-21","lastUpdated":"2025-11-21","url":"https://llmpricing.dev/m/allenai/olmo-3-32b-think/"},{"id":"sakana/sakana-namazu","name":"Sakana Namazu","lab":"sakana","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":[256000,262144],"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sakana","input":0.95,"output":4,"cacheRead":0.15,"official":true},"cheapest":{"provider":"openrouter","input":0.95,"output":4,"cacheRead":0.15},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":1.7125,"spread":1,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-08-03","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/sakana/sakana-namazu/"},{"id":"perplexity/sonar-deep-research-2","name":"Sonar Deep Research","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"edenai","input":2,"output":8,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":2,"output":8,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-02-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-deep-research-2/"},{"id":"perplexity/sonar-2","name":"Sonar","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[127000,130000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"perplexity","input":1,"output":1,"cacheRead":null,"official":true},"cheapest":{"provider":"perplexity-agent","input":0.25,"output":2.5,"cacheRead":0.0625},"blendedRef":1,"blendedMin":0.8125,"blendedTrusted":1,"spread":4,"hostCount":7,"pricedHostCount":6,"aa":{"idx":9.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-2/"},{"id":"perplexity/sonar-reasoning-pro-2","name":"Sonar Reasoning Pro","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[127000,128000],"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"perplexity","input":2,"output":8,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":2,"output":8,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":1,"hostCount":6,"pricedHostCount":4,"aa":{"idx":18,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-reasoning-pro-2/"},{"id":"perplexity/sonar-pro-2","name":"Sonar Pro","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"perplexity","input":3,"output":15,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":1,"hostCount":7,"pricedHostCount":5,"aa":{"idx":9.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-pro-2/"},{"id":"perplexity/sonar-pro-search","name":"Sonar Pro Search","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-30","lastUpdated":"2025-10-30","url":"https://llmpricing.dev/m/perplexity/sonar-pro-search/"},{"id":"thedrummer/cydonia-24b-v4.1-2","name":"Cydonia 24B V4.1","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.3,"output":0.5,"cacheRead":0.15,"official":false},"cheapest":{"provider":"openrouter","input":0.3,"output":0.5,"cacheRead":0.15},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-27","lastUpdated":"2025-09-27","url":"https://llmpricing.dev/m/thedrummer/cydonia-24b-v4.1-2/"},{"id":"thedrummer/skyfall-36b-v2-2","name":"Skyfall 36B V2","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.55,"output":0.8,"cacheRead":0.25,"official":false},"cheapest":{"provider":"openrouter","input":0.55,"output":0.8,"cacheRead":0.25},"blendedRef":0.6125,"blendedMin":0.6125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-10","lastUpdated":"2025-03-10","url":"https://llmpricing.dev/m/thedrummer/skyfall-36b-v2-2/"},{"id":"thedrummer/unslopnemo-12b","name":"UnslopNemo 12B","lab":"thedrummer","kind":"text","status":"ga","openWeights":true,"context":1024000,"contextRange":null,"outputLimit":1024000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.4,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.4,"output":0.4,"cacheRead":null},"blendedRef":0.4,"blendedMin":0.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-08","lastUpdated":"2024-11-08","url":"https://llmpricing.dev/m/thedrummer/unslopnemo-12b/"},{"id":"rekaai/reka-edge","name":"Reka Edge","lab":"rekaai","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text","video"],"reference":{"provider":"kilo","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-20","lastUpdated":"2026-03-20","url":"https://llmpricing.dev/m/rekaai/reka-edge/"},{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","lab":"rekaai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.1,"output":0.2,"cacheRead":null},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":3.7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/rekaai/reka-flash-3/"},{"id":"stealth/ox-alpha","name":"Ox Alpha","lab":"stealth","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/stealth/ox-alpha/"},{"id":"writer/palmyra-x5","name":"Palmyra X5","lab":"writer","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1040000],"outputLimit":250000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":0.6,"output":6,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.6,"output":6,"cacheRead":null},"blendedRef":1.95,"blendedMin":1.95,"blendedTrusted":1.95,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2026-01-21","url":"https://llmpricing.dev/m/writer/palmyra-x5/"},{"id":"mistral/ministral-8b-2512-2","name":"Ministral 3 8B 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.15,"output":0.15,"cacheRead":0.015,"official":false},"cheapest":{"provider":"openrouter","input":0.15,"output":0.15,"cacheRead":0.015},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-8b-2512-2/"},{"id":"mistral/mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"openrouter","input":0.09375,"output":0.25,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.09375,"output":0.25,"cacheRead":null},"blendedRef":0.1328,"blendedMin":0.1328,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2025-06-20","url":"https://llmpricing.dev/m/mistral/mistral-small-3.2-24b-instruct/"},{"id":"mistral/mistral-small-24b-instruct-2501","name":"Mistral Small 3","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.05,"output":0.08,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.05,"output":0.08,"cacheRead":null},"blendedRef":0.0575,"blendedMin":0.0575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":6.7,"coding":null,"agentic":null,"speed":142,"ttft":0.8,"taskCost":null},"usage":null,"releaseDate":"2025-01-30","lastUpdated":"2025-01-30","url":"https://llmpricing.dev/m/mistral/mistral-small-24b-instruct-2501/"},{"id":"mistral/voxtral-small-24b-2507-2","name":"Voxtral Small 24B 2507","lab":"mistral","kind":"audio","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio","pdf"],"reference":{"provider":"amazon-bedrock","input":0.15,"output":0.35,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.1,"output":0.3,"cacheRead":0.01},"blendedRef":0.2,"blendedMin":0.15,"blendedTrusted":0.2,"spread":1.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-30","lastUpdated":"2025-10-30","url":"https://llmpricing.dev/m/mistral/voxtral-small-24b-2507-2/"},{"id":"mistral/ministral-3b-2512-2","name":"Ministral 3 3B 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.1,"output":0.1,"cacheRead":0.01,"official":false},"cheapest":{"provider":"openrouter","input":0.1,"output":0.1,"cacheRead":0.01},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-3b-2512-2/"},{"id":"mistral/mistral-large-2407","name":"Mistral Large 2407","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"openrouter","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-11-19","lastUpdated":"2024-11-19","url":"https://llmpricing.dev/m/mistral/mistral-large-2407/"},{"id":"mistral/mistral-large-2","name":"Mistral Large","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":25600,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"openrouter","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":{"idx":4.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-02-26","lastUpdated":"2024-07-24","url":"https://llmpricing.dev/m/mistral/mistral-large-2/"},{"id":"mistral/mixtral-8x22b-instruct-2","name":"Mixtral 8x22B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"openrouter","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"openrouter","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-04-17","lastUpdated":"2024-04-17","url":"https://llmpricing.dev/m/mistral/mixtral-8x22b-instruct-2/"},{"id":"mistral/ministral-14b-2512-2","name":"Ministral 3 14B 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.2,"output":0.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"openrouter","input":0.2,"output":0.2,"cacheRead":0.02},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-14b-2512-2/"},{"id":"mistral/mistral-saba-2","name":"Saba","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"openrouter","input":0.2,"output":0.6,"cacheRead":0.02,"official":false},"cheapest":{"provider":"openrouter","input":0.2,"output":0.6,"cacheRead":0.02},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-17","lastUpdated":"2025-02-17","url":"https://llmpricing.dev/m/mistral/mistral-saba-2/"},{"id":"mistral/mistral-small-3-1-24b-instruct-2503","name":"Mistral Small 3.1 24B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.351,"output":0.555,"cacheRead":null,"official":false},"cheapest":{"provider":"watsonx","input":0.106,"output":0.318,"cacheRead":null},"blendedRef":0.402,"blendedMin":0.159,"blendedTrusted":null,"spread":3.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-03-17","lastUpdated":"2025-03-17","url":"https://llmpricing.dev/m/mistral/mistral-small-3-1-24b-instruct-2503/"},{"id":"morph/morph-v3-large","name":"Morph v3 Large","lab":"morph","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":[32000,262144],"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"morph","input":0.9,"output":1.9,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.9,"output":1.9,"cacheRead":null},"blendedRef":1.15,"blendedMin":1.15,"blendedTrusted":1.15,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-08-15","lastUpdated":"2025-07-07","url":"https://llmpricing.dev/m/morph/morph-v3-large/"},{"id":"morph/morph-v3-fast","name":"Morph v3 Fast","lab":"morph","kind":"text","status":"ga","openWeights":false,"context":16000,"contextRange":[16000,81920],"outputLimit":16000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"morph","input":0.8,"output":1.2,"cacheRead":null,"official":true},"cheapest":{"provider":"openrouter","input":0.8,"output":1.2,"cacheRead":null},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":0.9,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-08-15","lastUpdated":"2025-07-07","url":"https://llmpricing.dev/m/morph/morph-v3-fast/"},{"id":"amazon/nova-micro-v1-2","name":"Nova Micro 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":5120,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.035,"output":0.14,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.035,"output":0.14,"cacheRead":null},"blendedRef":0.0613,"blendedMin":0.0613,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-05","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/amazon/nova-micro-v1-2/"},{"id":"amazon/nova-premier-v1","name":"Nova Premier 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":2.5,"output":12.5,"cacheRead":0.625,"official":false},"cheapest":{"provider":"openrouter","input":2.5,"output":12.5,"cacheRead":0.625},"blendedRef":5,"blendedMin":5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-31","lastUpdated":"2025-10-31","url":"https://llmpricing.dev/m/amazon/nova-premier-v1/"},{"id":"amazon/nova-lite-v1-2","name":"Nova Lite 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":5120,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.06,"output":0.24,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-05","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/amazon/nova-lite-v1-2/"},{"id":"mancer/weaver","name":"Weaver (alpha)","lab":"mancer","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":6000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.5,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.5,"output":0.75,"cacheRead":null},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-08-02","lastUpdated":"2023-08-02","url":"https://llmpricing.dev/m/mancer/weaver/"},{"id":"meta/l3.1-euryale-70b","name":"Llama 3.1 Euryale 70B v2.2","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.85,"output":0.85,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.85,"output":0.85,"cacheRead":null},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-28","lastUpdated":"2024-08-28","url":"https://llmpricing.dev/m/meta/l3.1-euryale-70b/"},{"id":"meta/l3.3-euryale-70b","name":"Llama 3.3 Euryale 70B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.65,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.65,"output":0.75,"cacheRead":null},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-18","lastUpdated":"2024-12-18","url":"https://llmpricing.dev/m/meta/l3.3-euryale-70b/"},{"id":"meta/l3-lunaris-8b","name":"Llama 3 8B Lunaris","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.04,"output":0.05,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.04,"output":0.05,"cacheRead":null},"blendedRef":0.0425,"blendedMin":0.0425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-13","lastUpdated":"2024-08-13","url":"https://llmpricing.dev/m/meta/l3-lunaris-8b/"},{"id":"moonshotai/kimi-latest-2","name":"MoonshotAI Kimi Latest","lab":"moonshotai","kind":"text","status":"ga","openWeights":false,"context":974842,"contextRange":[974842,1048576],"outputLimit":974842,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":2.6,"output":13,"cacheRead":0.29,"official":false},"cheapest":{"provider":"openrouter","input":2.6,"output":13,"cacheRead":0.29},"blendedRef":5.2,"blendedMin":5.2,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/moonshotai/kimi-latest-2/"},{"id":"ibm-granite/granite-4.0-h-micro","name":"Granite 4.0 Micro","lab":"ibm-granite","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.017,"output":0.112,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.017,"output":0.112,"cacheRead":null},"blendedRef":0.0408,"blendedMin":0.0408,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-10-20","lastUpdated":"2025-10-20","url":"https://llmpricing.dev/m/ibm-granite/granite-4.0-h-micro/"},{"id":"dots-studio/dots-3-note-preview-free","name":"Dots3-Note Preview (free)","lab":"dots-studio","kind":"text","status":"ga","openWeights":false,"context":512000,"contextRange":null,"outputLimit":512000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openrouter","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/dots-studio/dots-3-note-preview-free/"},{"id":"relace/relace-search","name":"Relace Search","lab":"relace","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":1,"output":3,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/relace/relace-search/"},{"id":"relace/relace-apply-3","name":"Relace Apply 3","lab":"relace","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openrouter","input":0.85,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"openrouter","input":0.85,"output":1.25,"cacheRead":null},"blendedRef":0.95,"blendedMin":0.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-26","lastUpdated":"2025-09-26","url":"https://llmpricing.dev/m/relace/relace-apply-3/"},{"id":"alibaba/qwen3.6-35b-a3b-fp8","name":"Qwen3.6 35B A3B FP8","lab":"alibaba","kind":"text","status":"beta","openWeights":true,"context":262144,"contextRange":[131072,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"nearai","input":0.17,"output":1.1,"cacheRead":0.056,"official":false},"cheapest":{"provider":"nearai","input":0.17,"output":1.1,"cacheRead":0.056},"blendedRef":0.4025,"blendedMin":0.4025,"blendedTrusted":null,"spread":null,"hostCount":4,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-fp8/"},{"id":"alibaba/qwen3-reranker-4b","name":"Qwen3-Reranker-4B","lab":"alibaba","kind":"rerank","status":"ga","openWeights":true,"context":32768,"contextRange":[32000,32768],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"regolo-ai","input":0.12,"output":0.12,"cacheRead":null,"official":false},"cheapest":{"provider":"evroc","input":0.0575,"output":0,"cacheRead":null},"blendedRef":0.12,"blendedMin":0.0431,"blendedTrusted":0.0431,"spread":2.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-02-01","url":"https://llmpricing.dev/m/alibaba/qwen3-reranker-4b/"},{"id":"misc/brick-complexity-pro","name":"Brick Complexity Pro","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":100000,"contextRange":null,"outputLimit":15000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"regolo-ai","input":0.12,"output":0.46,"cacheRead":null,"official":false},"cheapest":{"provider":"regolo-ai","input":0.12,"output":0.46,"cacheRead":null},"blendedRef":0.205,"blendedMin":0.205,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-06","lastUpdated":"2026-02-06","url":"https://llmpricing.dev/m/misc/brick-complexity-pro/"},{"id":"alibaba/qwen3.5-122b","name":"Qwen3.5-122B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"regolo-ai","input":0.9,"output":3.6,"cacheRead":null,"official":false},"cheapest":{"provider":"regolo-ai","input":0.9,"output":3.6,"cacheRead":null},"blendedRef":1.575,"blendedMin":1.575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-02-01","url":"https://llmpricing.dev/m/alibaba/qwen3.5-122b/"},{"id":"misc/brick-v1-beta","name":"Brick v1 Beta","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":100000,"contextRange":null,"outputLimit":15000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"regolo-ai","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-06","lastUpdated":"2026-02-06","url":"https://llmpricing.dev/m/misc/brick-v1-beta/"},{"id":"openai/faster-whisper-large-v3","name":"Faster Whisper Large v3","lab":"openai","kind":"audio","status":"ga","openWeights":true,"context":448,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"regolo-ai","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/faster-whisper-large-v3/"},{"id":"deepseek/deepseek-ocr-2","name":"DeepSeek OCR 2","lab":"deepseek","kind":"text","status":"beta","openWeights":true,"context":8192,"contextRange":[4000,8192],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"privatemode-ai","input":0.8897,"output":1.4675,"cacheRead":0.0924,"official":false},"cheapest":{"provider":"privatemode-ai","input":0.8897,"output":1.4675,"cacheRead":0.0924},"blendedRef":1.0342,"blendedMin":1.0342,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/deepseek/deepseek-ocr-2/"},{"id":"misc/lynkr-auto","name":"Lynkr Auto (complexity routing)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"lynkr","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2026-07-11","url":"https://llmpricing.dev/m/misc/lynkr-auto/"},{"id":"amazon/lucidnova-rf1-100b","name":"LucidNova RF1 100B","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":120000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"lucidquery","input":2,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"lucidquery","input":2,"output":5,"cacheRead":null},"blendedRef":2.75,"blendedMin":2.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-28","lastUpdated":"2025-09-10","url":"https://llmpricing.dev/m/amazon/lucidnova-rf1-100b/"},{"id":"misc/lucidquery-nexus-coder","name":"LucidQuery Nexus Coder","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":250000,"contextRange":null,"outputLimit":60000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"lucidquery","input":2,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"lucidquery","input":2,"output":5,"cacheRead":null},"blendedRef":2.75,"blendedMin":2.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/misc/lucidquery-nexus-coder/"},{"id":"misc/lucidquery-agi-01-frontier","name":"AGI-01 Frontier","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":120000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"lucidquery","input":4.5,"output":22,"cacheRead":null,"official":false},"cheapest":{"provider":"lucidquery","input":4.5,"output":22,"cacheRead":null},"blendedRef":8.875,"blendedMin":8.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-16","lastUpdated":"2026-06-16","url":"https://llmpricing.dev/m/misc/lucidquery-agi-01-frontier/"},{"id":"misc/lucidquery-agi-01-swift","name":"AGI-01 Swift","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":120000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"lucidquery","input":2.5,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"lucidquery","input":2.5,"output":15,"cacheRead":null},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-16","lastUpdated":"2026-06-16","url":"https://llmpricing.dev/m/misc/lucidquery-agi-01-swift/"},{"id":"moonshotai/kimi-k2-thinking-turbo","name":"Kimi K2 Thinking Turbo","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[262000,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"moonshotai","input":1.15,"output":8,"cacheRead":0.15,"official":true},"cheapest":{"provider":"moonshotai","input":1.15,"output":8,"cacheRead":0.15},"blendedRef":2.8625,"blendedMin":2.8625,"blendedTrusted":2.8625,"spread":1.1,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-11-06","lastUpdated":"2025-11-06","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-thinking-turbo/"},{"id":"moonshotai/kimi-k2-turbo-preview","name":"Kimi K2 Turbo","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"moonshotai","input":2.4,"output":10,"cacheRead":0.6,"official":true},"cheapest":{"provider":"moonshotai","input":2.4,"output":10,"cacheRead":0.6},"blendedRef":4.3,"blendedMin":4.3,"blendedTrusted":4.3,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-05","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-turbo-preview/"},{"id":"nvidia/nemotron-3-super-120b-a12b-free-2","name":"Nemotron 3 Super 120B A12B (Free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kenari","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b-free-2/"},{"id":"zhipuai/glm-4-7-flash-free","name":"GLM-4.7-Flash (Free)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kenari","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4-7-flash-free/"},{"id":"xiaomi/mimo-v2-5-free","name":"MiMo-V2.5 (Free)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":[200000,1048576],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"kenari","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-5-free/"},{"id":"moonshotai/kimi-k2-7-code-free","name":"Kimi K2.7 Code (Free)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kenari","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-7-code-free/"},{"id":"deepseek/deepseek-v4-flash-free","name":"DeepSeek V4 Flash (Free)","lab":"deepseek","kind":"text","status":"deprecated","openWeights":true,"context":1000000,"contextRange":[200000,1000000],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kenari","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-07-31","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-free/"},{"id":"openai/gpt-image-2","name":"GPT-Image-2","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":[128000,272000],"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"openai","input":5,"output":30,"cacheRead":1.25,"official":true},"cheapest":{"provider":"openai","input":5,"output":30,"cacheRead":1.25},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":11.25,"spread":1,"hostCount":6,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/openai/gpt-image-2/"},{"id":"moonshotai/kimi-k2-6-free","name":"Kimi K2.6 (Free)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kenari","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-6-free/"},{"id":"arcee-ai/trinity-mini","name":"Trinity Mini","lab":"arcee-ai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.045,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"clarifai","input":0.045,"output":0.15,"cacheRead":null},"blendedRef":0.0713,"blendedMin":0.0713,"blendedTrusted":0.0713,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/arcee-ai/trinity-mini/"},{"id":"clarifai/mm-poly-8b","name":"MM Poly 8B","lab":"clarifai","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"clarifai","input":0.658,"output":1.11,"cacheRead":null,"official":true},"cheapest":{"provider":"clarifai","input":0.658,"output":1.11,"cacheRead":null},"blendedRef":0.771,"blendedMin":0.771,"blendedTrusted":0.771,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/clarifai/mm-poly-8b/"},{"id":"openai/gpt-oss-120b-high-throughput","name":"GPT OSS 120B High Throughput","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"clarifai","input":0.09,"output":0.36,"cacheRead":null,"official":false},"cheapest":{"provider":"clarifai","input":0.09,"output":0.36,"cacheRead":null},"blendedRef":0.1575,"blendedMin":0.1575,"blendedTrusted":0.1575,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-high-throughput/"},{"id":"deepseek/deepseek-ocr","name":"DeepSeek OCR","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"clarifai","input":0.2,"output":0.7,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.03,"output":0.03,"cacheRead":null},"blendedRef":0.325,"blendedMin":0.03,"blendedTrusted":0.325,"spread":6.7,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-20","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/deepseek/deepseek-ocr/"},{"id":"mistral/ministral-3-3b-reasoning-2512","name":"Ministral 3 3B Reasoning 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"clarifai","input":1.039,"output":0.54825,"cacheRead":null,"official":false},"cheapest":{"provider":"clarifai","input":1.039,"output":0.54825,"cacheRead":null},"blendedRef":0.9163,"blendedMin":0.9163,"blendedTrusted":0.9163,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/mistral/ministral-3-3b-reasoning-2512/"},{"id":"mistral/ministral-3-14b-reasoning-2512","name":"Ministral 3 14B Reasoning 2512","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"clarifai","input":2.5,"output":1.7,"cacheRead":null,"official":false},"cheapest":{"provider":"clarifai","input":2.5,"output":1.7,"cacheRead":null},"blendedRef":2.3,"blendedMin":2.3,"blendedTrusted":2.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-12","url":"https://llmpricing.dev/m/mistral/ministral-3-14b-reasoning-2512/"},{"id":"minimax/minimax-m2-5-high-throughput","name":"MiniMax-M2.5 High Throughput","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"clarifai","input":0.3,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"clarifai","input":0.3,"output":1.2,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":0.525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/minimax/minimax-m2-5-high-throughput/"},{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"mistral","input":0.5,"output":1.5,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":0.75,"spread":8,"hostCount":5,"pricedHostCount":4,"aa":{"idx":9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral-large-latest/"},{"id":"cohere/c4ai-aya-expanse-32b","name":"Aya Expanse 32B","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-24","lastUpdated":"2024-10-24","url":"https://llmpricing.dev/m/cohere/c4ai-aya-expanse-32b/"},{"id":"cohere/command-a-reasoning-08-2025-2","name":"Command A Reasoning","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/cohere/command-a-reasoning-08-2025-2/"},{"id":"cohere/c4ai-aya-vision-32b","name":"Aya Vision 32B","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":16000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-04","lastUpdated":"2025-05-14","url":"https://llmpricing.dev/m/cohere/c4ai-aya-vision-32b/"},{"id":"cohere/command-a-translate-08-2025","name":"Command A Translate","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-28","lastUpdated":"2025-08-28","url":"https://llmpricing.dev/m/cohere/command-a-translate-08-2025/"},{"id":"cohere/command-r7b-arabic-02-2025","name":"Command R7B Arabic","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":0.0375,"output":0.15,"cacheRead":null,"official":true},"cheapest":{"provider":"cohere","input":0.0375,"output":0.15,"cacheRead":null},"blendedRef":0.0656,"blendedMin":0.0656,"blendedTrusted":0.0656,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-27","lastUpdated":"2025-02-27","url":"https://llmpricing.dev/m/cohere/command-r7b-arabic-02-2025/"},{"id":"cohere/c4ai-aya-expanse-8b","name":"Aya Expanse 8B","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":8000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-24","lastUpdated":"2024-10-24","url":"https://llmpricing.dev/m/cohere/c4ai-aya-expanse-8b/"},{"id":"cohere/command-a-vision-07-2025","name":"Command A Vision","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-31","lastUpdated":"2025-07-31","url":"https://llmpricing.dev/m/cohere/command-a-vision-07-2025/"},{"id":"cohere/command-a-plus-05-2026-2","name":"Command A Plus","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"cohere","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-20","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/cohere/command-a-plus-05-2026-2/"},{"id":"cohere/north-mini-code-1-0","name":"North Mini Code","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cohere","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":20.2,"coding":36.5,"agentic":3.1,"speed":26,"ttft":0.49,"taskCost":0},"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/cohere/north-mini-code-1-0/"},{"id":"cohere/c4ai-aya-vision-8b","name":"Aya Vision 8B","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":16000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-03-04","lastUpdated":"2025-05-14","url":"https://llmpricing.dev/m/cohere/c4ai-aya-vision-8b/"},{"id":"zhipuai/glm-4.5-flash","name":"GLM-4.5-Flash","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[131072,200000],"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":0,"output":0,"cacheRead":0,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":4,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-flash/"},{"id":"zhipuai/glm-4.7-flashx","name":"GLM-4.7-FlashX","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zai","input":0.07,"output":0.4,"cacheRead":0.01,"official":true},"cheapest":{"provider":"vercel","input":0.06,"output":0.4,"cacheRead":0.01},"blendedRef":0.1525,"blendedMin":0.145,"blendedTrusted":0.145,"spread":1.2,"hostCount":8,"pricedHostCount":8,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flashx/"},{"id":"moonshotai/kimi-k2.6-nitro","name":"Kimi K2.6 Nitro","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"routing-run","input":0.275,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"routing-run","input":0.275,"output":1.1,"cacheRead":null},"blendedRef":0.4813,"blendedMin":0.4813,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-nitro/"},{"id":"moonshotai/kimi-k2.7-code-nitro","name":"Kimi K2.7 Code Nitro","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"routing-run","input":0.275,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"routing-run","input":0.275,"output":1.1,"cacheRead":null},"blendedRef":0.4813,"blendedMin":0.4813,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-nitro/"},{"id":"zhipuai/glm-5.2-nitro","name":"GLM 5.2 Nitro","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"routing-run","input":0.8,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"routing-run","input":0.8,"output":2.4,"cacheRead":null},"blendedRef":1.2,"blendedMin":1.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-nitro/"},{"id":"mistral/e5-mistral-7b-instruct","name":"E5 Mistral 7B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":4096,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"stackit","input":0.02,"output":0.02,"cacheRead":null,"official":false},"cheapest":{"provider":"stackit","input":0.02,"output":0.02,"cacheRead":null},"blendedRef":0.02,"blendedMin":0.02,"blendedTrusted":0.02,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-12-11","lastUpdated":"2023-12-11","url":"https://llmpricing.dev/m/mistral/e5-mistral-7b-instruct/"},{"id":"alibaba/qwen3-vl-235b-a22b-instruct-fp8","name":"Qwen3-VL 235B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":218000,"contextRange":[128000,218000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"stackit","input":1.76,"output":2.05,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":0.21,"output":1.9,"cacheRead":0.1},"blendedRef":1.8325,"blendedMin":0.6325,"blendedTrusted":1.8325,"spread":8.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-instruct-fp8/"},{"id":"alibaba/qwen3-vl-embedding-8b","name":"Qwen3-VL Embedding 8B","lab":"alibaba","kind":"embedding","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"stackit","input":0.09,"output":0.09,"cacheRead":null,"official":false},"cheapest":{"provider":"stackit","input":0.09,"output":0.09,"cacheRead":null},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":0.09,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-embedding-8b/"},{"id":"misc/tongyi-intent-detect-v3","name":"Tongyi Intent Detect V3","lab":"misc","kind":"classify","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.058,"output":0.144,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.058,"output":0.144,"cacheRead":null},"blendedRef":0.0795,"blendedMin":0.0795,"blendedTrusted":0.0795,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01","lastUpdated":"2024-01","url":"https://llmpricing.dev/m/misc/tongyi-intent-detect-v3/"},{"id":"alibaba/qwen-omni-turbo","name":"Qwen-Omni Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba-cn","input":0.058,"output":0.23,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.058,"output":0.23,"cacheRead":null},"blendedRef":0.101,"blendedMin":0.101,"blendedTrusted":0.101,"spread":3.4,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-01-19","lastUpdated":"2025-03-26","url":"https://llmpricing.dev/m/alibaba/qwen-omni-turbo/"},{"id":"alibaba/qwen-vl-max","name":"Qwen-VL Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.23,"output":0.574,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.23,"output":0.574,"cacheRead":null},"blendedRef":0.316,"blendedMin":0.316,"blendedTrusted":0.316,"spread":3.5,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-04-08","lastUpdated":"2025-08-13","url":"https://llmpricing.dev/m/alibaba/qwen-vl-max/"},{"id":"alibaba/qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"alibaba-cn","input":0.108,"output":0.431,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.108,"output":0.431,"cacheRead":null},"blendedRef":0.1888,"blendedMin":0.1888,"blendedTrusted":0.1888,"spread":1.9,"hostCount":2,"pricedHostCount":2,"aa":{"idx":13.4,"coding":null,"agentic":null,"speed":111,"ttft":2.16,"taskCost":null},"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-30b-a3b/"},{"id":"alibaba/deepseek-r1-distill-qwen-1-5b","name":"DeepSeek R1 Distill Qwen 1.5B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":3.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/alibaba/deepseek-r1-distill-qwen-1-5b/"},{"id":"alibaba/qwen-math-plus","name":"Qwen Math Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.574,"output":1.721,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.574,"output":1.721,"cacheRead":null},"blendedRef":0.8608,"blendedMin":0.8608,"blendedTrusted":0.8608,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-16","lastUpdated":"2024-09-19","url":"https://llmpricing.dev/m/alibaba/qwen-math-plus/"},{"id":"deepseek/deepseek-r1-distill-llama-8b","name":"DeepSeek R1 Distill Llama 8B","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":6.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-distill-llama-8b/"},{"id":"alibaba/qwen-max-2","name":"Qwen Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[32768,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.345,"output":1.377,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.345,"output":1.377,"cacheRead":null},"blendedRef":0.603,"blendedMin":0.603,"blendedTrusted":0.603,"spread":4.6,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2024-04-03","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-max-2/"},{"id":"alibaba/qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder 7B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.144,"output":0.287,"cacheRead":null},"blendedRef":0.1797,"blendedMin":0.1797,"blendedTrusted":0.1797,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":4.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-11","lastUpdated":"2024-11","url":"https://llmpricing.dev/m/alibaba/qwen2-5-coder-7b-instruct/"},{"id":"alibaba/qwen-math-turbo","name":"Qwen Math Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.287,"output":0.861,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.287,"output":0.861,"cacheRead":null},"blendedRef":0.4305,"blendedMin":0.4305,"blendedTrusted":0.4305,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-19","lastUpdated":"2024-09-19","url":"https://llmpricing.dev/m/alibaba/qwen-math-turbo/"},{"id":"alibaba/qwen-vl-ocr","name":"Qwen-VL OCR","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":34096,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"alibaba-cn","input":0.717,"output":0.717,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.717,"output":0.717,"cacheRead":null},"blendedRef":0.717,"blendedMin":0.717,"blendedTrusted":0.717,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-10-28","lastUpdated":"2025-04-13","url":"https://llmpricing.dev/m/alibaba/qwen-vl-ocr/"},{"id":"alibaba/qwen-plus-character","name":"Qwen Plus Character","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.115,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.115,"output":0.287,"cacheRead":null},"blendedRef":0.158,"blendedMin":0.158,"blendedTrusted":0.158,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01","lastUpdated":"2024-01","url":"https://llmpricing.dev/m/alibaba/qwen-plus-character/"},{"id":"alibaba/qwen-mt-turbo","name":"Qwen-MT Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.101,"output":0.28,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.101,"output":0.28,"cacheRead":null},"blendedRef":0.1458,"blendedMin":0.1458,"blendedTrusted":0.1458,"spread":1.6,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01","lastUpdated":"2025-01","url":"https://llmpricing.dev/m/alibaba/qwen-mt-turbo/"},{"id":"alibaba/qwen3-omni-flash","name":"Qwen3-Omni Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba-cn","input":0.058,"output":0.23,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.058,"output":0.23,"cacheRead":null},"blendedRef":0.101,"blendedMin":0.101,"blendedTrusted":0.101,"spread":7.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-15","lastUpdated":"2025-09-15","url":"https://llmpricing.dev/m/alibaba/qwen3-omni-flash/"},{"id":"moonshotai/kimi-k2.5-3","name":"Moonshot Kimi K2.5","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.574,"output":2.411,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.574,"output":2.411,"cacheRead":null},"blendedRef":1.0333,"blendedMin":1.0333,"blendedTrusted":1.0333,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-3/"},{"id":"alibaba/qwen-deep-research","name":"Qwen Deep Research","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":7.742,"output":23.367,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":7.742,"output":23.367,"cacheRead":null},"blendedRef":11.6483,"blendedMin":11.6483,"blendedTrusted":11.6483,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01","lastUpdated":"2024-01","url":"https://llmpricing.dev/m/alibaba/qwen-deep-research/"},{"id":"alibaba/qwen-flash","name":"Qwen Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.022,"output":0.216,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.022,"output":0.216,"cacheRead":null},"blendedRef":0.0705,"blendedMin":0.0705,"blendedTrusted":0.0705,"spread":2.3,"hostCount":7,"pricedHostCount":7,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/alibaba/qwen-flash/"},{"id":"moonshotai/moonshot-kimi-k2-instruct","name":"Moonshot Kimi K2 Instruct","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.574,"output":2.294,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.574,"output":2.294,"cacheRead":null},"blendedRef":1.004,"blendedMin":1.004,"blendedTrusted":1.004,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/moonshotai/moonshot-kimi-k2-instruct/"},{"id":"deepseek/deepseek-r1-distill-llama-70b-2","name":"DeepSeek R1 Distill Llama 70B","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":32678,"contextRange":[8192,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.99,"output":0.99,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.03,"output":0.13,"cacheRead":null},"blendedRef":0.99,"blendedMin":0.055,"blendedTrusted":0.4305,"spread":33,"hostCount":6,"pricedHostCount":6,"aa":{"idx":9.8,"coding":null,"agentic":null,"speed":25,"ttft":1.02,"taskCost":null},"usage":null,"releaseDate":"2025-01-23","lastUpdated":"2025-01-30","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-distill-llama-70b-2/"},{"id":"alibaba/deepseek-r1-distill-qwen-7b","name":"DeepSeek R1 Distill Qwen 7B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.072,"output":0.144,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.072,"output":0.144,"cacheRead":null},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":0.09,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/alibaba/deepseek-r1-distill-qwen-7b/"},{"id":"alibaba/qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba-cn","input":0.087,"output":0.345,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.087,"output":0.345,"cacheRead":null},"blendedRef":0.1515,"blendedMin":0.1515,"blendedTrusted":0.1515,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12","lastUpdated":"2024-12","url":"https://llmpricing.dev/m/alibaba/qwen2-5-omni-7b/"},{"id":"alibaba/qvq-max-2","name":"QVQ Max","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"alibaba-cn","input":1.147,"output":4.588,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":1.147,"output":4.588,"cacheRead":null},"blendedRef":2.0073,"blendedMin":2.0073,"blendedTrusted":2.0073,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-03-25","lastUpdated":"2025-03-25","url":"https://llmpricing.dev/m/alibaba/qvq-max-2/"},{"id":"alibaba/qwen-doc-turbo","name":"Qwen Doc Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.087,"output":0.144,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.087,"output":0.144,"cacheRead":null},"blendedRef":0.1013,"blendedMin":0.1013,"blendedTrusted":0.1013,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01","lastUpdated":"2024-01","url":"https://llmpricing.dev/m/alibaba/qwen-doc-turbo/"},{"id":"alibaba/qwen-long-2","name":"Qwen Long","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":10000000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.072,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.072,"output":0.287,"cacheRead":null},"blendedRef":0.1257,"blendedMin":0.1257,"blendedTrusted":0.1257,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-25","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-long-2/"},{"id":"alibaba/qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba-cn","input":0.23,"output":0.918,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.23,"output":0.918,"cacheRead":null},"blendedRef":0.402,"blendedMin":0.402,"blendedTrusted":0.402,"spread":2.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-15","lastUpdated":"2025-09-15","url":"https://llmpricing.dev/m/alibaba/qwen3-omni-flash-realtime/"},{"id":"alibaba/qwen2-5-14b-instruct","name":"Qwen2.5 14B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.431,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.144,"output":0.431,"cacheRead":null},"blendedRef":0.2158,"blendedMin":0.2158,"blendedTrusted":0.2158,"spread":2.4,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2024-09-19","url":"https://llmpricing.dev/m/alibaba/qwen2-5-14b-instruct/"},{"id":"alibaba/qwen-mt-plus","name":"Qwen-MT Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.259,"output":0.775,"cacheRead":null,"official":true},"cheapest":{"provider":"novita-ai","input":0.25,"output":0.75,"cacheRead":null},"blendedRef":0.388,"blendedMin":0.375,"blendedTrusted":0.388,"spread":9.8,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-01","lastUpdated":"2025-09-03","url":"https://llmpricing.dev/m/alibaba/qwen-mt-plus/"},{"id":"alibaba/qwen2-5-math-72b-instruct","name":"Qwen2.5-Math 72B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":4096,"contextRange":null,"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.574,"output":1.721,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.574,"output":1.721,"cacheRead":null},"blendedRef":0.8608,"blendedMin":0.8608,"blendedTrusted":0.8608,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/alibaba/qwen2-5-math-72b-instruct/"},{"id":"alibaba/qwq-plus","name":"QwQ Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.23,"output":0.574,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.23,"output":0.574,"cacheRead":null},"blendedRef":0.316,"blendedMin":0.316,"blendedTrusted":0.316,"spread":3.5,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-03-05","lastUpdated":"2025-03-05","url":"https://llmpricing.dev/m/alibaba/qwq-plus/"},{"id":"alibaba/deepseek-r1-distill-qwen-14b","name":"DeepSeek R1 Distill Qwen 14B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.431,"cacheRead":null,"official":true},"cheapest":{"provider":"novita-ai","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.2158,"blendedMin":0.15,"blendedTrusted":0.2158,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":9.7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-20","url":"https://llmpricing.dev/m/alibaba/deepseek-r1-distill-qwen-14b/"},{"id":"alibaba/qwen2-5-math-7b-instruct","name":"Qwen2.5-Math 7B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":4096,"contextRange":null,"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.144,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.144,"output":0.287,"cacheRead":null},"blendedRef":0.1797,"blendedMin":0.1797,"blendedTrusted":0.1797,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/alibaba/qwen2-5-math-7b-instruct/"},{"id":"alibaba/qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","audio"],"reference":{"provider":"alibaba-cn","input":0.23,"output":0.918,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.23,"output":0.918,"cacheRead":null},"blendedRef":0.402,"blendedMin":0.402,"blendedTrusted":0.402,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-08","lastUpdated":"2025-05-08","url":"https://llmpricing.dev/m/alibaba/qwen-omni-turbo-realtime/"},{"id":"alibaba/qwen3-asr-flash","name":"Qwen3-ASR Flash","lab":"alibaba","kind":"audio","status":"ga","openWeights":false,"context":53248,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"alibaba-cn","input":0.032,"output":0.032,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.032,"output":0.032,"cacheRead":null},"blendedRef":0.032,"blendedMin":0.032,"blendedTrusted":0.032,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-08","lastUpdated":"2025-09-08","url":"https://llmpricing.dev/m/alibaba/qwen3-asr-flash/"},{"id":"alibaba/qwen2-5-32b-instruct","name":"Qwen2.5 32B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.287,"output":0.861,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.287,"output":0.861,"cacheRead":null},"blendedRef":0.4305,"blendedMin":0.4305,"blendedTrusted":0.4305,"spread":2.4,"hostCount":2,"pricedHostCount":2,"aa":{"idx":7.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-09","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/alibaba/qwen2-5-32b-instruct/"},{"id":"alibaba/qwen-vl-plus","name":"Qwen-VL Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.115,"output":0.287,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba-cn","input":0.115,"output":0.287,"cacheRead":null},"blendedRef":0.158,"blendedMin":0.158,"blendedTrusted":0.158,"spread":1.8,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2025-08-15","url":"https://llmpricing.dev/m/alibaba/qwen-vl-plus/"},{"id":"moonshotai/kimi-k2-thinking-2","name":"Moonshot Kimi K2 Thinking","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.574,"output":2.294,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.574,"output":2.294,"cacheRead":null},"blendedRef":1.004,"blendedMin":1.004,"blendedTrusted":1.004,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-06","lastUpdated":"2025-11-06","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-thinking-2/"},{"id":"moonshotai/kimi-k2.6-3","name":"Moonshot Kimi K2.6","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.929,"output":3.858,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.929,"output":3.858,"cacheRead":null},"blendedRef":1.6613,"blendedMin":1.6613,"blendedTrusted":1.6613,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-3/"},{"id":"moonshotai/kimi-k2.5-4","name":"kimi/kimi-k2.5","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"alibaba-cn","input":0.6,"output":3,"cacheRead":0.1,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.6,"output":3,"cacheRead":0.1},"blendedRef":1.2,"blendedMin":1.2,"blendedTrusted":1.2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-4/"},{"id":"deepseek/deepseek-v3.1-terminus-3","name":"siliconflow/deepseek-v3.1-terminus","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.27,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.27,"output":1,"cacheRead":null},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":0.4525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus-3/"},{"id":"deepseek/deepseek-v3-0324-3","name":"siliconflow/deepseek-v3-0324","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.25,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.25,"output":1,"cacheRead":null},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-26","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3-0324-3/"},{"id":"deepseek/deepseek-v3.2-3","name":"siliconflow/deepseek-v3.2","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.27,"output":0.42,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.27,"output":0.42,"cacheRead":null},"blendedRef":0.3075,"blendedMin":0.3075,"blendedTrusted":0.3075,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-03","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-3/"},{"id":"deepseek/deepseek-r1-0528-3","name":"siliconflow/deepseek-r1-0528","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba-cn","input":0.5,"output":2.18,"cacheRead":null,"official":false},"cheapest":{"provider":"alibaba-cn","input":0.5,"output":2.18,"cacheRead":null},"blendedRef":0.92,"blendedMin":0.92,"blendedTrusted":0.92,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-28","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-0528-3/"},{"id":"anthropic/us.anthropic.claude-fable-5","name":"Claude Fable 5 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"amazon-bedrock","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":20,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-fable-5/"},{"id":"anthropic/jp.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":4,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-sonnet-5/"},{"id":"anthropic/jp.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-opus-4-7/"},{"id":"anthropic/jp.anthropic.claude-sonnet-4-5-20250929-v1-0","name":"Claude Sonnet 4.5 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-sonnet-4-5-20250929-v1-0/"},{"id":"anthropic/au.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (AU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":4,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-sonnet-5/"},{"id":"anthropic/global.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-sonnet-4-6/"},{"id":"anthropic/au.anthropic.claude-sonnet-4-6","name":"AU Anthropic Claude Sonnet 4.6","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3.3,"output":16.5,"cacheRead":0.33,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3.3,"output":16.5,"cacheRead":0.33},"blendedRef":6.6,"blendedMin":6.6,"blendedTrusted":6.6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-02-17","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-sonnet-4-6/"},{"id":"openai/global.openai.gpt-5.6-sol","name":"GPT-5.6 Sol (Global)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5.5,"output":33,"cacheRead":0.55,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5.5,"output":33,"cacheRead":0.55},"blendedRef":12.375,"blendedMin":12.375,"blendedTrusted":12.375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/global.openai.gpt-5.6-sol/"},{"id":"anthropic/jp.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-sonnet-4-6/"},{"id":"mistral/mistral.ministral-3-3b-instruct","name":"Ministral 3 3B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":0.1,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":7.1,"coding":4.8,"agentic":1.6,"speed":203,"ttft":0.64,"taskCost":0.1297},"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral.ministral-3-3b-instruct/"},{"id":"anthropic/global.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":4,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-sonnet-5/"},{"id":"anthropic/eu.anthropic.claude-opus-5","name":"Claude Opus 5 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5.5,"output":27.5,"cacheRead":0.55,"official":false},"cheapest":{"provider":"requesty","input":4.95,"output":24.75,"cacheRead":0.495},"blendedRef":11,"blendedMin":9.9,"blendedTrusted":11,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-opus-5/"},{"id":"deepseek/us.deepseek.r1-v1-0","name":"DeepSeek-R1 (US)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":1.35,"output":5.4,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":1.35,"output":5.4,"cacheRead":null},"blendedRef":2.3625,"blendedMin":2.3625,"blendedTrusted":2.3625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-20","lastUpdated":"2025-05-29","url":"https://llmpricing.dev/m/deepseek/us.deepseek.r1-v1-0/"},{"id":"anthropic/us.anthropic.claude-opus-4-1-20250805-v1-0","name":"Claude Opus 4.1 (US)","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":30,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-opus-4-1-20250805-v1-0/"},{"id":"meta/us.meta.llama4-maverick-17b-instruct-v1-0","name":"Llama 4 Maverick 17B Instruct (US)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.24,"output":0.97,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.24,"output":0.97,"cacheRead":null},"blendedRef":0.4225,"blendedMin":0.4225,"blendedTrusted":0.4225,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/us.meta.llama4-maverick-17b-instruct-v1-0/"},{"id":"anthropic/eu.anthropic.claude-fable-5","name":"Claude Fable 5 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":11,"output":55,"cacheRead":1.1,"official":false},"cheapest":{"provider":"requesty","input":9.9,"output":49.5,"cacheRead":0.99},"blendedRef":22,"blendedMin":19.8,"blendedTrusted":22,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-fable-5/"},{"id":"anthropic/jp.anthropic.claude-haiku-4-5-20251001-v1-0","name":"Claude Haiku 4.5 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-haiku-4-5-20251001-v1-0/"},{"id":"anthropic/au.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (AU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-opus-4-8/"},{"id":"anthropic/global.anthropic.claude-sonnet-4-5-20250929-v1-0","name":"Claude Sonnet 4.5 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-sonnet-4-5-20250929-v1-0/"},{"id":"anthropic/eu.anthropic.claude-haiku-4-5-20251001-v1-0","name":"Claude Haiku 4.5 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":1.1,"output":5.5,"cacheRead":0.11,"official":false},"cheapest":{"provider":"amazon-bedrock","input":1.1,"output":5.5,"cacheRead":0.11},"blendedRef":2.2,"blendedMin":2.2,"blendedTrusted":2.2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-haiku-4-5-20251001-v1-0/"},{"id":"anthropic/au.anthropic.claude-sonnet-4-5-20250929-v1-0","name":"Claude Sonnet 4.5 (AU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-sonnet-4-5-20250929-v1-0/"},{"id":"meta/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[430000,1048576],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"neon","input":0.5,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":0.14,"output":0.59,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.2525,"blendedTrusted":0.4225,"spread":3.6,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-instruct/"},{"id":"anthropic/us.anthropic.claude-opus-5","name":"Claude Opus 5 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-opus-5/"},{"id":"amazon/amazon.nova-pro-v1-0","name":"Nova Pro","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"vercel","input":0.8,"output":3.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.8,"output":3.2,"cacheRead":0.2},"blendedRef":1.4,"blendedMin":1.4,"blendedTrusted":1.4,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":7.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-03","url":"https://llmpricing.dev/m/amazon/amazon.nova-pro-v1-0/"},{"id":"alibaba/qwen3-vl-235b-a22b-instruct-2","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0.3,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.3,"output":1.5,"cacheRead":null},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":0.6,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-10-04","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-instruct-2/"},{"id":"meta/us.meta.llama4-scout-17b-instruct-v1-0","name":"Llama 4 Scout 17B Instruct (US)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":3500000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.17,"output":0.66,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.17,"output":0.66,"cacheRead":null},"blendedRef":0.2925,"blendedMin":0.2925,"blendedTrusted":0.2925,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/us.meta.llama4-scout-17b-instruct-v1-0/"},{"id":"writer/writer.palmyra-x4-v1-0","name":"Palmyra X4","lab":"writer","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[122880,128000],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/writer/writer.palmyra-x4-v1-0/"},{"id":"nvidia/nvidia.nemotron-super-3-120b","name":"NVIDIA Nemotron 3 Super 120B A12B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.15,"output":0.65,"cacheRead":null,"official":false},"cheapest":{"provider":"requesty","input":0.09,"output":0.45,"cacheRead":null},"blendedRef":0.275,"blendedMin":0.18,"blendedTrusted":0.275,"spread":1.7,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nvidia.nemotron-super-3-120b/"},{"id":"anthropic/us.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-opus-4-8/"},{"id":"anthropic/global.anthropic.claude-fable-5","name":"Claude Fable 5 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"amazon-bedrock","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":20,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-fable-5/"},{"id":"anthropic/global.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-opus-4-8/"},{"id":"anthropic/eu.anthropic.claude-opus-4-5-20251101-v1-0","name":"Claude Opus 4.5 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5.5,"output":27.5,"cacheRead":0.55,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5.5,"output":27.5,"cacheRead":0.55},"blendedRef":11,"blendedMin":11,"blendedTrusted":11,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-08-01","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-opus-4-5-20251101-v1-0/"},{"id":"google/google.gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":198000,"contextRange":[198000,202752],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"venice","input":0.12,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.12,"output":0.2,"cacheRead":null},"blendedRef":0.14,"blendedMin":0.14,"blendedTrusted":0.14,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-27","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/google/google.gemma-3-27b-it/"},{"id":"anthropic/jp.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-opus-4-8/"},{"id":"mistral/mistral.magistral-small-2509","name":"Magistral Small 1.2","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":40000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.5,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":0.75,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":11.5,"coding":14.7,"agentic":1.5,"speed":143,"ttft":0.83,"taskCost":0.295},"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral.magistral-small-2509/"},{"id":"anthropic/global.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-opus-4-7/"},{"id":"anthropic/jp.anthropic.claude-opus-5","name":"Claude Opus 5 (JP)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/jp.anthropic.claude-opus-5/"},{"id":"anthropic/global.anthropic.claude-haiku-4-5-20251001-v1-0","name":"Claude Haiku 4.5 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-haiku-4-5-20251001-v1-0/"},{"id":"anthropic/au.anthropic.claude-opus-4-6-v1","name":"AU Anthropic Claude Opus 4.6","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":16.5,"output":82.5,"cacheRead":1.65,"official":false},"cheapest":{"provider":"amazon-bedrock","input":16.5,"output":82.5,"cacheRead":1.65},"blendedRef":33,"blendedMin":33,"blendedTrusted":33,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-opus-4-6-v1/"},{"id":"mistral/mistral.ministral-3-8b-instruct","name":"Ministral 3 8B","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,262144],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.15,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":{"idx":9,"coding":9.7,"agentic":1.2,"speed":120,"ttft":0.72,"taskCost":0.1846},"usage":null,"releaseDate":"2024-12-01","lastUpdated":"2025-12-15","url":"https://llmpricing.dev/m/mistral/mistral.ministral-3-8b-instruct/"},{"id":"anthropic/us.anthropic.claude-haiku-4-5-20251001-v1-0","name":"Claude Haiku 4.5 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-haiku-4-5-20251001-v1-0/"},{"id":"amazon/amazon.nova-lite-v1-0","name":"Nova Lite","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"vercel","input":0.06,"output":0.24,"cacheRead":0.015,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.06,"output":0.24,"cacheRead":0.015},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":0.105,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":6.7,"coding":null,"agentic":null,"speed":155,"ttft":0.94,"taskCost":null},"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-03","url":"https://llmpricing.dev/m/amazon/amazon.nova-lite-v1-0/"},{"id":"nvidia/nvidia.nemotron-nano-12b-v2","name":"NVIDIA Nemotron Nano 12B v2 VL BF16","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.2,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.2,"output":0.6,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":0.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-01","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/nvidia/nvidia.nemotron-nano-12b-v2/"},{"id":"anthropic/eu.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3.3,"output":16.5,"cacheRead":0.33,"official":false},"cheapest":{"provider":"requesty","input":2.97,"output":14.85,"cacheRead":0.27},"blendedRef":6.6,"blendedMin":5.94,"blendedTrusted":6.6,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-sonnet-4-6/"},{"id":"anthropic/global.anthropic.claude-opus-4-5-20251101-v1-0","name":"Claude Opus 4.5 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-08-01","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-opus-4-5-20251101-v1-0/"},{"id":"anthropic/eu.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2.2,"output":11,"cacheRead":0.22,"official":false},"cheapest":{"provider":"requesty","input":1.98,"output":9.9,"cacheRead":0.198},"blendedRef":4.4,"blendedMin":3.96,"blendedTrusted":4.4,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-sonnet-5/"},{"id":"anthropic/us.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"amazon-bedrock","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":4,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-sonnet-5/"},{"id":"alibaba/qwen.qwen3-32b-v1-0","name":"Qwen3 32B (dense)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-18","lastUpdated":"2025-09-18","url":"https://llmpricing.dev/m/alibaba/qwen.qwen3-32b-v1-0/"},{"id":"anthropic/au.anthropic.claude-haiku-4-5-20251001-v1-0","name":"Claude Haiku 4.5 (AU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"amazon-bedrock","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-haiku-4-5-20251001-v1-0/"},{"id":"openai/global.openai.gpt-5.6-luna","name":"GPT-5.6 Luna (Global)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":0.22,"output":1.32,"cacheRead":0.022,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.22,"output":1.32,"cacheRead":0.022},"blendedRef":0.495,"blendedMin":0.495,"blendedTrusted":0.495,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/global.openai.gpt-5.6-luna/"},{"id":"anthropic/us.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-opus-4-7/"},{"id":"anthropic/us.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-sonnet-4-6/"},{"id":"mistral/mistral.voxtral-mini-3b-2507","name":"Voxtral Mini 3B 2507","lab":"mistral","kind":"audio","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["audio","text"],"reference":{"provider":"amazon-bedrock","input":0.04,"output":0.04,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.04,"output":0.04,"cacheRead":null},"blendedRef":0.04,"blendedMin":0.04,"blendedTrusted":0.04,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-01","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/mistral/mistral.voxtral-mini-3b-2507/"},{"id":"google/gemma-3-12b-it-3","name":"Google Gemma 3 12B","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.05,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.049999999999999996,"output":0.09999999999999999,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.0625,"blendedTrusted":0.0625,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-12-01","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/google/gemma-3-12b-it-3/"},{"id":"amazon/amazon.nova-micro-v1-0","name":"Nova Micro","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.035,"output":0.14,"cacheRead":0.00875,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.035,"output":0.14,"cacheRead":0.00875},"blendedRef":0.0613,"blendedMin":0.0613,"blendedTrusted":0.0613,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":4.4,"coding":null,"agentic":null,"speed":282,"ttft":0.87,"taskCost":null},"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-03","url":"https://llmpricing.dev/m/amazon/amazon.nova-micro-v1-0/"},{"id":"alibaba/qwen.qwen3-next-80b-a3b","name":"Qwen/Qwen3-Next-80B-A3B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":0.14,"output":1.4,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.14,"output":1.4,"cacheRead":null},"blendedRef":0.455,"blendedMin":0.455,"blendedTrusted":0.455,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-18","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen.qwen3-next-80b-a3b/"},{"id":"anthropic/au.anthropic.claude-opus-5","name":"Claude Opus 5 (AU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/au.anthropic.claude-opus-5/"},{"id":"anthropic/us.anthropic.claude-sonnet-4-5-20250929-v1-0","name":"Claude Sonnet 4.5 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-sonnet-4-5-20250929-v1-0/"},{"id":"openai/global.openai.gpt-5.6-terra","name":"GPT-5.6 Terra (Global)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":2.2,"output":13.2,"cacheRead":0.22,"official":false},"cheapest":{"provider":"amazon-bedrock","input":2.2,"output":13.2,"cacheRead":0.22},"blendedRef":4.95,"blendedMin":4.95,"blendedTrusted":4.95,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/global.openai.gpt-5.6-terra/"},{"id":"anthropic/global.anthropic.claude-opus-5","name":"Claude Opus 5 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-opus-5/"},{"id":"meta/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":3500000,"contextRange":[131072,3500000],"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"amazon-bedrock","input":0.17,"output":0.66,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.18,"output":0.59,"cacheRead":null},"blendedRef":0.2925,"blendedMin":0.2825,"blendedTrusted":0.2925,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-instruct/"},{"id":"anthropic/us.anthropic.claude-opus-4-5-20251101-v1-0","name":"Claude Opus 4.5 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-08-01","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-opus-4-5-20251101-v1-0/"},{"id":"anthropic/us.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (US)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/us.anthropic.claude-opus-4-6-v1/"},{"id":"anthropic/eu.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5.5,"output":27.5,"cacheRead":0.55,"official":false},"cheapest":{"provider":"requesty","input":4.95,"output":24.75,"cacheRead":0.495},"blendedRef":11,"blendedMin":9.9,"blendedTrusted":11,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-opus-4-8/"},{"id":"nvidia/nvidia.nemotron-nano-3-30b","name":"NVIDIA Nemotron Nano 3 30B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.06,"output":0.24,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":0.105,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/nvidia/nvidia.nemotron-nano-3-30b/"},{"id":"anthropic/eu.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5.5,"output":27.5,"cacheRead":0.55,"official":false},"cheapest":{"provider":"requesty","input":4.95,"output":24.75,"cacheRead":0.495},"blendedRef":11,"blendedMin":9.9,"blendedTrusted":11,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-opus-4-7/"},{"id":"anthropic/eu.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5.5,"output":27.5,"cacheRead":0.55,"official":false},"cheapest":{"provider":"requesty","input":4.95,"output":24.75,"cacheRead":0.495},"blendedRef":11,"blendedMin":9.9,"blendedTrusted":11,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-opus-4-6-v1/"},{"id":"anthropic/eu.anthropic.claude-sonnet-4-5-20250929-v1-0","name":"Claude Sonnet 4.5 (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":3.3,"output":16.5,"cacheRead":0.33,"official":false},"cheapest":{"provider":"amazon-bedrock","input":3.3,"output":16.5,"cacheRead":0.33},"blendedRef":6.6,"blendedMin":6.6,"blendedTrusted":6.6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/eu.anthropic.claude-sonnet-4-5-20250929-v1-0/"},{"id":"anthropic/global.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (Global)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"amazon-bedrock","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/global.anthropic.claude-opus-4-6-v1/"},{"id":"mistral/mistral.ministral-3-14b-instruct","name":"Ministral 14B 3.0","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"amazon-bedrock","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"amazon-bedrock","input":0.2,"output":0.2,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":0.2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-01","lastUpdated":"2024-12-01","url":"https://llmpricing.dev/m/mistral/mistral.ministral-3-14b-instruct/"},{"id":"openai/gpt-image-1.5","name":"GPT-Image-1.5","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":{"provider":"azure","input":5,"output":32,"cacheRead":1.25},"blendedRef":null,"blendedMin":11.75,"blendedTrusted":11.75,"spread":1,"hostCount":4,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-25","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/openai/gpt-image-1.5/"},{"id":"openai/gpt-image-1-mini","name":"gpt-image-1-mini","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":{"provider":"vercel","input":2,"output":8,"cacheRead":0.2},"blendedRef":null,"blendedMin":3.5,"blendedTrusted":3.5,"spread":null,"hostCount":3,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-26","lastUpdated":"2025-10-06","url":"https://llmpricing.dev/m/openai/gpt-image-1-mini/"},{"id":"openai/text-embedding-ada-002","name":"text-embedding-ada-002","lab":"openai","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openai","input":0.1,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"openai","input":0.1,"output":0,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":0.075,"spread":1,"hostCount":4,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2022-12-15","lastUpdated":"2022-12-15","url":"https://llmpricing.dev/m/openai/text-embedding-ada-002/"},{"id":"openai/gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"openai","input":1.75,"output":14,"cacheRead":0.175,"official":true},"cheapest":{"provider":"openai","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":4.8125,"spread":1,"hostCount":4,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/gpt-5.3-codex-spark/"},{"id":"openai/gpt-image-1","name":"GPT-Image-1","lab":"openai","kind":"image","status":"deprecated","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":{"provider":"digitalocean","input":5,"output":40,"cacheRead":1.25},"blendedRef":null,"blendedMin":13.75,"blendedTrusted":13.75,"spread":1,"hostCount":5,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-24","lastUpdated":"2025-04-24","url":"https://llmpricing.dev/m/openai/gpt-image-1/"},{"id":"openai/gpt-realtime-2.1","name":"GPT-Realtime-2.1","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","audio","image"],"reference":{"provider":"openai","input":4,"output":24,"cacheRead":0.4,"official":true},"cheapest":{"provider":"openai","input":4,"output":24,"cacheRead":0.4},"blendedRef":9,"blendedMin":9,"blendedTrusted":9,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/openai/gpt-realtime-2.1/"},{"id":"openai/chatgpt-image-latest","name":"chatgpt-image-latest","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/openai/chatgpt-image-latest/"},{"id":"openai/text-embedding-3-small","name":"text-embedding-3-small","lab":"openai","kind":"embedding","status":"ga","openWeights":false,"context":8191,"contextRange":[8191,8192],"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openai","input":0.02,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"openai","input":0.02,"output":0,"cacheRead":null},"blendedRef":0.015,"blendedMin":0.015,"blendedTrusted":0.015,"spread":1,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":{"rank":64,"tokens":49712847809,"share":0.00018630174344307567},"releaseDate":"2024-01-25","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/text-embedding-3-small/"},{"id":"openai/text-embedding-3-large","name":"text-embedding-3-large","lab":"openai","kind":"embedding","status":"ga","openWeights":false,"context":8191,"contextRange":[8191,8192],"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"openai","input":0.13,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"sap-ai-core","input":0.09,"output":0,"cacheRead":null},"blendedRef":0.0975,"blendedMin":0.0675,"blendedTrusted":0.0675,"spread":1.4,"hostCount":5,"pricedHostCount":4,"aa":null,"usage":{"rank":69,"tokens":24592608413,"share":0.00009216220806254617},"releaseDate":"2024-01-25","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/text-embedding-3-large/"},{"id":"deepseek/deepseek-v4-pro-2","name":"DeepSeek V4 Pro (New)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode-go","input":0.66,"output":1.98,"cacheRead":0.022,"official":false},"cheapest":{"provider":"opencode-go","input":0.66,"output":1.98,"cacheRead":0.022},"blendedRef":0.99,"blendedMin":0.99,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-2/"},{"id":"xiaomi/mimo-v2-omni","name":"MiMo-V2-Omni","lab":"xiaomi","kind":"text","status":"deprecated","openWeights":false,"context":262144,"contextRange":[262144,265000],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","pdf","video"],"reference":{"provider":"xiaomi","input":0.14,"output":0.28,"cacheRead":0.0028,"official":true},"cheapest":{"provider":"xiaomi","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":0.175,"spread":2.9,"hostCount":3,"pricedHostCount":3,"aa":{"idx":35.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/xiaomi/mimo-v2-omni/"},{"id":"tencent/hy3-3","name":"Hy3 (8x usage)","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode-go","input":0.0175,"output":0.0725,"cacheRead":0.004375,"official":false},"cheapest":{"provider":"opencode-go","input":0.0175,"output":0.0725,"cacheRead":0.004375},"blendedRef":0.0313,"blendedMin":0.0313,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3-3/"},{"id":"xai/grok-imagine-video","name":"Grok Imagine Video","lab":"xai","kind":"video","status":"ga","openWeights":false,"context":1024,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-28","lastUpdated":"2026-01-28","url":"https://llmpricing.dev/m/xai/grok-imagine-video/"},{"id":"xai/grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","lab":"xai","kind":"video","status":"ga","openWeights":false,"context":1024,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-30","lastUpdated":"2026-05-30","url":"https://llmpricing.dev/m/xai/grok-imagine-video-1.5/"},{"id":"xai/grok-imagine-image-quality","name":"Grok Imagine Image Quality","lab":"xai","kind":"image","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-03","lastUpdated":"2026-04-03","url":"https://llmpricing.dev/m/xai/grok-imagine-image-quality/"},{"id":"xai/grok-imagine-image-2.0","name":"Grok Imagine Image 2.0","lab":"xai","kind":"image","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-07","lastUpdated":"2026-08-07","url":"https://llmpricing.dev/m/xai/grok-imagine-image-2.0/"},{"id":"xai/grok-imagine-image","name":"Grok Imagine Image","lab":"xai","kind":"image","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-28","lastUpdated":"2026-01-28","url":"https://llmpricing.dev/m/xai/grok-imagine-image/"},{"id":"misc/step-1-32k","name":"Step 1 (32K)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"stepfun","input":2.05,"output":9.59,"cacheRead":0.41,"official":false},"cheapest":{"provider":"stepfun-ai","input":2.05,"output":9.59,"cacheRead":0.41},"blendedRef":3.935,"blendedMin":3.935,"blendedTrusted":3.935,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/misc/step-1-32k/"},{"id":"stepfun/stepaudio-2.5-tts","name":"StepAudio 2.5 TTS","lab":"stepfun","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/stepfun/stepaudio-2.5-tts/"},{"id":"misc/step-2-16k","name":"Step 2 (16K)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"stepfun","input":5.21,"output":16.44,"cacheRead":1.04,"official":false},"cheapest":{"provider":"stepfun-ai","input":5.21,"output":16.44,"cacheRead":1.04},"blendedRef":8.0175,"blendedMin":8.0175,"blendedTrusted":8.0175,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/misc/step-2-16k/"},{"id":"stepfun/stepaudio-2.5-asr","name":"StepAudio 2.5 ASR","lab":"stepfun","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/stepfun/stepaudio-2.5-asr/"},{"id":"stepfun/step-tts-2","name":"Step TTS 2","lab":"stepfun","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/stepfun/step-tts-2/"},{"id":"alibaba/qwen3-30b-a3b-2507","name":"Qwen3 30B A3B 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"lmstudio","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":14.6,"coding":12.1,"agentic":1.8,"speed":138,"ttft":2.39,"taskCost":0.0787},"usage":null,"releaseDate":"2025-07-30","lastUpdated":"2025-07-30","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b-2507/"},{"id":"alibaba/qwen3-coder-30b","name":"Qwen3 Coder 30B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"lmstudio","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-30b/"},{"id":"zhipuai/large","name":"Ambient Large","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":202752,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"ambient","input":0.6,"output":2,"cacheRead":0.15,"official":false},"cheapest":{"provider":"ambient","input":0.6,"output":2,"cacheRead":0.15},"blendedRef":0.95,"blendedMin":0.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/large/"},{"id":"google/gemini-3.1-pro-preview-2","name":"Gemini 3.1 Pro (Preview) (Quartz)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-2/"},{"id":"moonshotai/kimi-k3-3","name":"Kimi K3 (Fireworks AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1040384,"contextRange":null,"outputLimit":1040384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-3/"},{"id":"deepseek/deepseek-v4-flash-3","name":"DeepSeek V4 Flash (Fireworks AI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.028,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-3/"},{"id":"moonshotai/kimi-k3-fast-2","name":"Kimi K3 Fast (Fireworks AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1040384,"contextRange":null,"outputLimit":1040384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":4.5,"output":22.5,"cacheRead":0.45,"official":false},"cheapest":{"provider":"llmgateway-providers","input":4.5,"output":22.5,"cacheRead":0.45},"blendedRef":9,"blendedMin":9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-fast-2/"},{"id":"deepseek/deepseek-v4-pro-3","name":"DeepSeek V4 Pro (Fireworks AI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.32,"output":3.96,"cacheRead":0.044,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.32,"output":3.96,"cacheRead":0.044},"blendedRef":1.98,"blendedMin":1.98,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-3/"},{"id":"deepseek/deepseek-v4-flash-4","name":"DeepSeek V4 Flash (DeepSeek)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[1000000,1050000],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.154,"output":0.308,"cacheRead":0.0308,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.1925,"blendedMin":0.175,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-4/"},{"id":"deepseek/deepseek-v4-pro-4","name":"DeepSeek V4 Pro (DeepSeek)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":[1000000,1050000],"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.478,"output":0.956,"cacheRead":0.004302,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.435,"output":0.87,"cacheRead":0.003625},"blendedRef":0.5975,"blendedMin":0.5438,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-4/"},{"id":"google/gemini-3.5-flash-lite-2","name":"Gemini 3.5 Flash Lite (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-lite-2/"},{"id":"google/gemini-3.1-pro-preview-3","name":"Gemini 3.1 Pro (Preview) (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-3/"},{"id":"google/gemini-2.5-flash-lite-2","name":"Gemini 2.5 Flash Lite (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.01},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-2/"},{"id":"google/gemini-3.5-flash-2","name":"Gemini 3.5 Flash (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":1.5,"output":9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.5,"output":9,"cacheRead":0.15},"blendedRef":3.375,"blendedMin":3.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-2/"},{"id":"google/gemini-3.1-flash-lite-2","name":"Gemini 3.1 Flash Lite (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":1.5,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite-2/"},{"id":"google/gemini-2.5-flash-2","name":"Gemini 2.5 Flash (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-2/"},{"id":"google/gemini-3.6-flash-2","name":"Gemini 3.6 Flash (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.6-flash-2/"},{"id":"google/gemini-3-flash-preview-2","name":"Gemini 3 Flash (Preview) (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-17","lastUpdated":"2025-12-17","url":"https://llmpricing.dev/m/google/gemini-3-flash-preview-2/"},{"id":"google/gemini-2.5-pro-2","name":"Gemini 2.5 Pro (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-2/"},{"id":"google/gemini-3.7-flash-2","name":"Gemini 3.7 Flash (Google Vertex AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-13","lastUpdated":"2026-08-13","url":"https://llmpricing.dev/m/google/gemini-3.7-flash-2/"},{"id":"google/gemma-4-26b-a4b-it-3","name":"Gemma 4 26B A4B IT (DeepInfra)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.07,"output":0.34,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.07,"output":0.34,"cacheRead":null},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-it-3/"},{"id":"deepseek/deepseek-v4-flash-5","name":"DeepSeek V4 Flash (DeepInfra)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.08,"output":0.18,"cacheRead":0.016,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.08,"output":0.18,"cacheRead":0.016},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-5/"},{"id":"nvidia/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra 550B (DeepInfra)","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":2.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":2.2,"cacheRead":0.1},"blendedRef":0.925,"blendedMin":0.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b/"},{"id":"deepseek/deepseek-v4-pro-5","name":"DeepSeek V4 Pro (DeepInfra)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.3,"output":2.6,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.3,"output":2.6,"cacheRead":0.1},"blendedRef":1.625,"blendedMin":1.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-5/"},{"id":"deepseek/deepseek-v3.2-4","name":"DeepSeek V3.2 (DeepInfra)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":160000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.26,"output":0.38,"cacheRead":0.13,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.26,"output":0.38,"cacheRead":0.13},"blendedRef":0.29,"blendedMin":0.29,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-4/"},{"id":"deepinfra/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash (DeepInfra)","lab":"deepinfra","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.06,"output":0.18,"cacheRead":0.012,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.06,"output":0.18,"cacheRead":0.012},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-02","lastUpdated":"2026-08-02","url":"https://llmpricing.dev/m/deepinfra/ling-3.0-flash/"},{"id":"google/gemma-4-31b-it-3","name":"Gemma 4 31B IT (DeepInfra)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.13,"output":0.38,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.13,"output":0.38,"cacheRead":null},"blendedRef":0.1925,"blendedMin":0.1925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-3/"},{"id":"moonshotai/kimi-k2.5-5","name":"Kimi K2.5 (DeepInfra)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.45,"output":2.25,"cacheRead":0.07,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.45,"output":2.25,"cacheRead":0.07},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-5/"},{"id":"alibaba/qwen3.5-9b-2","name":"Qwen3.5 9B (DeepInfra)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.15,"cacheRead":null},"blendedRef":0.1125,"blendedMin":0.1125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-23","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/alibaba/qwen3.5-9b-2/"},{"id":"zhipuai/glm-5.1-3","name":"GLM-5.1 (DeepInfra)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":198000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.05,"output":3.5,"cacheRead":0.205,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.05,"output":3.5,"cacheRead":0.205},"blendedRef":1.6625,"blendedMin":1.6625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-3/"},{"id":"tencent/hy3-4","name":"Hy3 (DeepInfra)","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.58,"cacheRead":0.035,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.58,"cacheRead":0.035},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3-4/"},{"id":"deepinfra/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct (DeepInfra)","lab":"deepinfra","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-05","lastUpdated":"2025-10-05","url":"https://llmpricing.dev/m/deepinfra/qwen3-vl-30b-a3b-instruct/"},{"id":"alibaba/qwen3-vl-235b-a22b-instruct-3","name":"Qwen3 VL 235B A22B Instruct (DeepInfra)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.88,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.88,"cacheRead":0.11},"blendedRef":0.37,"blendedMin":0.37,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-instruct-3/"},{"id":"meta/muse-spark-1.2-2","name":"Muse Spark 1.2 (Meta)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":4.25,"cacheRead":0.15,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":4.25,"cacheRead":0.15},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-05","lastUpdated":"2026-08-05","url":"https://llmpricing.dev/m/meta/muse-spark-1.2-2/"},{"id":"meta/muse-spark-1.1-2","name":"Muse Spark 1.1 (Meta)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","video"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":4.25,"cacheRead":0.15,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":4.25,"cacheRead":0.15},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-08","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/meta/muse-spark-1.1-2/"},{"id":"zhipuai/glm-4.6-3","name":"GLM-4.6 (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.55,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.55,"output":2.2,"cacheRead":0.11},"blendedRef":0.9625,"blendedMin":0.9625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-3/"},{"id":"moonshotai/kimi-k2.7-code-3","name":"Kimi K2.7 Code (NovitaAI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.19,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.19},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-3/"},{"id":"google/gemma-4-26b-a4b-it-4","name":"Gemma 4 26B A4B IT (NovitaAI)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.13,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.13,"output":0.4,"cacheRead":null},"blendedRef":0.1975,"blendedMin":0.1975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-26b-a4b-it-4/"},{"id":"alibaba/qwen3-coder-30b-a3b-instruct-2","name":"Qwen3 Coder 30B A3B Instruct (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":160000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.07,"output":0.27,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.07,"output":0.27,"cacheRead":null},"blendedRef":0.12,"blendedMin":0.12,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-30b-a3b-instruct-2/"},{"id":"alibaba/qwen3.7-max-2","name":"Qwen3.7 Max (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":3.75,"cacheRead":0.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":3.75,"cacheRead":0.25},"blendedRef":1.875,"blendedMin":1.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-21","lastUpdated":"2026-05-21","url":"https://llmpricing.dev/m/alibaba/qwen3.7-max-2/"},{"id":"novita/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B FP8 (NovitaAI)","lab":"novita","kind":"text","status":"ga","openWeights":false,"context":40960,"contextRange":null,"outputLimit":20000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/novita/qwen3-235b-a22b-fp8/"},{"id":"moonshotai/kimi-k3-4","name":"Kimi K3 (NovitaAI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-4/"},{"id":"meta/llama-3.2-3b-instruct-2","name":"Llama 3.2 3B Instruct (NovitaAI)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.03,"output":0.05,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.03,"output":0.05,"cacheRead":null},"blendedRef":0.035,"blendedMin":0.035,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-18","lastUpdated":"2024-09-18","url":"https://llmpricing.dev/m/meta/llama-3.2-3b-instruct-2/"},{"id":"zhipuai/glm-4.7-4","name":"GLM-4.7 (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-4/"},{"id":"zhipuai/glm-4.5v-2","name":"GLM-4.5V (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":1.8,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":1.8,"cacheRead":0.11},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-11","lastUpdated":"2025-08-11","url":"https://llmpricing.dev/m/zhipuai/glm-4.5v-2/"},{"id":"deepseek/deepseek-v4-flash-6","name":"DeepSeek V4 Flash (NovitaAI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1050000,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.028,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-6/"},{"id":"novita/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507 (NovitaAI)","lab":"novita","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":3,"cacheRead":null},"blendedRef":0.975,"blendedMin":0.975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2025-07-25","url":"https://llmpricing.dev/m/novita/qwen3-235b-a22b-thinking-2507/"},{"id":"meta/llama-3.3-70b-instruct-2","name":"Llama 3.3 70B Instruct (NovitaAI)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":120000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.135,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.135,"output":0.4,"cacheRead":null},"blendedRef":0.2013,"blendedMin":0.2013,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct-2/"},{"id":"alibaba/qwen3-vl-235b-a22b-thinking-2","name":"Qwen3 VL 235B A22B Thinking (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.98,"output":3.95,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.98,"output":3.95,"cacheRead":null},"blendedRef":1.7225,"blendedMin":1.7225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-thinking-2/"},{"id":"meta/llama-4-scout-17b-instruct-2","name":"Llama 4 Scout 17B Instruct (NovitaAI)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.18,"output":0.59,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.18,"output":0.59,"cacheRead":null},"blendedRef":0.2825,"blendedMin":0.2825,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-instruct-2/"},{"id":"deepseek/deepseek-v3.2-5","name":"DeepSeek V3.2 (NovitaAI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.269,"output":0.4,"cacheRead":0.1345,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.269,"output":0.4,"cacheRead":0.1345},"blendedRef":0.3018,"blendedMin":0.3018,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-5/"},{"id":"novita/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash (NovitaAI)","lab":"novita","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.06,"output":0.18,"cacheRead":0.012,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.06,"output":0.18,"cacheRead":0.012},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-02","lastUpdated":"2026-08-02","url":"https://llmpricing.dev/m/novita/ling-3.0-flash/"},{"id":"moonshotai/kimi-k2-2","name":"Kimi K2 (NovitaAI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.57,"output":2.3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.57,"output":2.3,"cacheRead":null},"blendedRef":1.0025,"blendedMin":1.0025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-11","lastUpdated":"2025-07-11","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-2/"},{"id":"google/gemma-4-31b-it-4","name":"Gemma 4 31B IT (NovitaAI)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.4,"cacheRead":null},"blendedRef":0.205,"blendedMin":0.205,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-4/"},{"id":"zhipuai/glm-5-3","name":"GLM-5 (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.2},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-3/"},{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7 (NovitaAI)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/minimax-m2.7/"},{"id":"alibaba/qwen3.8-max-2","name":"Qwen3.8 Max (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.25},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-03","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/alibaba/qwen3.8-max-2/"},{"id":"alibaba/qwen35-397b-a17b","name":"Qwen3.5 397B A17B (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":3.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":3.6,"cacheRead":null},"blendedRef":1.35,"blendedMin":1.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen35-397b-a17b/"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct-2","name":"Qwen3 Coder 480B A35B Instruct (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.38,"output":1.55,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.38,"output":1.55,"cacheRead":null},"blendedRef":0.6725,"blendedMin":0.6725,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-480b-a35b-instruct-2/"},{"id":"alibaba/qwen3-max-2","name":"Qwen3 Max (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.845,"output":3.38,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.845,"output":3.38,"cacheRead":null},"blendedRef":1.4788,"blendedMin":1.4788,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-max-2/"},{"id":"zhipuai/glm-5.2-3","name":"GLM-5.2 (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-3/"},{"id":"zhipuai/glm-4.6v-2","name":"GLM-4.6V (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":0.055,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":0.055},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-2/"},{"id":"meta/llama-3-70b-instruct","name":"Llama 3 70B Instruct (NovitaAI)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.51,"output":0.74,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.51,"output":0.74,"cacheRead":null},"blendedRef":0.5675,"blendedMin":0.5675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-18","lastUpdated":"2024-04-18","url":"https://llmpricing.dev/m/meta/llama-3-70b-instruct/"},{"id":"minimax/minimax-m2.5-2","name":"MiniMax M2.5 (NovitaAI)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-2/"},{"id":"alibaba/qwen3.6-35b-a3b-3","name":"Qwen3.6 35B A3B (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"llmgateway-providers","input":0.248,"output":1.485,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.248,"output":1.485,"cacheRead":null},"blendedRef":0.5573,"blendedMin":0.5573,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-3/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507-3","name":"Qwen3 235B A22B Instruct 2507 (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.09,"output":0.58,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.09,"output":0.58,"cacheRead":null},"blendedRef":0.2125,"blendedMin":0.2125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-07-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507-3/"},{"id":"alibaba/qwen3-next-80b-a3b-instruct-2","name":"Qwen3 Next 80B A3B Instruct (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":1.5,"cacheRead":null},"blendedRef":0.4875,"blendedMin":0.4875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09","lastUpdated":"2025-09","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-instruct-2/"},{"id":"zhipuai/glm-5.1-4","name":"GLM-5.1 (NovitaAI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.38,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.38,"output":4.4,"cacheRead":0.26},"blendedRef":2.135,"blendedMin":2.135,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-4/"},{"id":"meta/llama-4-maverick-17b-instruct-2","name":"Llama 4 Maverick 17B Instruct (NovitaAI)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.27,"output":0.85,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.27,"output":0.85,"cacheRead":null},"blendedRef":0.415,"blendedMin":0.415,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-instruct-2/"},{"id":"baidu/ernie-4.5-vl-424b-a47b-2","name":"ERNIE 4.5 VL 424B A47B (NovitaAI)","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":123000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.42,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.42,"output":1.25,"cacheRead":null},"blendedRef":0.6275,"blendedMin":0.6275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/baidu/ernie-4.5-vl-424b-a47b-2/"},{"id":"tencent/hy3-5","name":"Hy3 (NovitaAI)","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.58,"cacheRead":0.035,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.58,"cacheRead":0.035},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3-5/"},{"id":"novita/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct (NovitaAI)","lab":"novita","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.7,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.7,"cacheRead":null},"blendedRef":0.325,"blendedMin":0.325,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-05","lastUpdated":"2025-10-05","url":"https://llmpricing.dev/m/novita/qwen3-vl-30b-a3b-instruct/"},{"id":"alibaba/qwen3-vl-235b-a22b-instruct-4","name":"Qwen3 VL 235B A22B Instruct (NovitaAI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.5,"cacheRead":null},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-instruct-4/"},{"id":"minimax/minimax-m2.1-2","name":"MiniMax M2.1 (NovitaAI)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/minimax-m2.1-2/"},{"id":"moonshotai/kimi-k2.6-4","name":"Kimi K2.6 (NovitaAI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.8,"output":3.4,"cacheRead":0.16,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.8,"output":3.4,"cacheRead":0.16},"blendedRef":1.45,"blendedMin":1.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-4/"},{"id":"anthropic/claude-opus-4-7-2","name":"Claude Opus 4.7 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-7-2/"},{"id":"anthropic/claude-opus-4-8-2","name":"Claude Opus 4.8 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-8-2/"},{"id":"anthropic/claude-sonnet-5-2","name":"Claude Sonnet 5 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-5-2/"},{"id":"anthropic/claude-sonnet-4-5-20250929-3","name":"Claude Sonnet 4.5 (2025-09-29) (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-20250929-3/"},{"id":"anthropic/claude-sonnet-4-6-2","name":"Claude Sonnet 4.6 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-6-2/"},{"id":"anthropic/claude-haiku-4-5-20251001-3","name":"Claude Haiku 4.5 (2025-10-01) (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-20251001-3/"},{"id":"anthropic/claude-sonnet-4-5-2","name":"Claude Sonnet 4.5 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-2/"},{"id":"anthropic/claude-opus-4-5-20251101-3","name":"Claude Opus 4.5 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2025-11-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-20251101-3/"},{"id":"anthropic/claude-fable-5-2","name":"Claude Fable 5 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/claude-fable-5-2/"},{"id":"anthropic/claude-haiku-4-5-2","name":"Claude Haiku 4.5 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-2/"},{"id":"anthropic/claude-opus-4-6-2","name":"Claude Opus 4.6 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-6-2/"},{"id":"anthropic/claude-opus-5-2","name":"Claude Opus 5 (Anthropic)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/claude-opus-5-2/"},{"id":"zhipuai/glm-4.6-4","name":"GLM-4.6 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/zhipuai/glm-4.6-4/"},{"id":"zhipuai/glm-4.7-5","name":"GLM-4.7 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-5/"},{"id":"zhipuai/glm-4.5v-3","name":"GLM-4.5V (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":1.8,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":1.8,"cacheRead":0.11},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-11","lastUpdated":"2025-08-11","url":"https://llmpricing.dev/m/zhipuai/glm-4.5v-3/"},{"id":"zhipuai/glm-4.5-x","name":"GLM-4.5 X (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":2.2,"output":8.9,"cacheRead":0.45,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.2,"output":8.9,"cacheRead":0.45},"blendedRef":3.875,"blendedMin":3.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-x/"},{"id":"zhipuai/glm-4.7-flashx-2","name":"GLM-4.7 FlashX (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.07,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.07,"output":0.4,"cacheRead":0.01},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flashx-2/"},{"id":"zhipuai/glm-5-4","name":"GLM-5 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.2},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-4/"},{"id":"zhipuai/glm-4-32b-0414-128k","name":"GLM-4 32B (0414-128k) (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/zhipuai/glm-4-32b-0414-128k/"},{"id":"zhipuai/glm-4.6v-flashx","name":"GLM-4.6V FlashX (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.04,"output":0.4,"cacheRead":0.004,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.04,"output":0.4,"cacheRead":0.004},"blendedRef":0.13,"blendedMin":0.13,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-flashx/"},{"id":"zhipuai/glm-5.3-3","name":"GLM-5.3 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/zhipuai/glm-5.3-3/"},{"id":"zhipuai/glm-4.5-airx","name":"GLM-4.5 AirX (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.1,"output":4.5,"cacheRead":0.22,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.1,"output":4.5,"cacheRead":0.22},"blendedRef":1.95,"blendedMin":1.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-airx/"},{"id":"zhipuai/glm-5.2-4","name":"GLM-5.2 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-4/"},{"id":"zhipuai/glm-4.6v-3","name":"GLM-4.6V (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":0.05},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-3/"},{"id":"zhipuai/glm-4.5-air-2","name":"GLM-4.5 Air (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":98304,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.1,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.1,"cacheRead":0.03},"blendedRef":0.425,"blendedMin":0.425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-air-2/"},{"id":"zhipuai/glm-5.1-5","name":"GLM-5.1 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"aihubmix","input":0.845,"output":3.38,"cacheRead":0.183112},"blendedRef":2.15,"blendedMin":1.4788,"blendedTrusted":null,"spread":1.7,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-5/"},{"id":"zhipuai/glm-4.5-2","name":"GLM-4.5 (Z AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-2/"},{"id":"zhipuai/glm-4.7-6","name":"GLM-4.7 (ByteDance)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-6/"},{"id":"deepseek/deepseek-v4-flash-7","name":"DeepSeek V4 Flash (ByteDance)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.44,"output":1.32,"cacheRead":0.014,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.44,"output":1.32,"cacheRead":0.014},"blendedRef":0.66,"blendedMin":0.66,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-7/"},{"id":"deepseek/deepseek-v4-pro-6","name":"DeepSeek V4 Pro (ByteDance)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.32,"output":3.96,"cacheRead":0.044,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.32,"output":3.96,"cacheRead":0.044},"blendedRef":1.98,"blendedMin":1.98,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-6/"},{"id":"deepseek/deepseek-v3.2-6","name":"DeepSeek V3.2 (ByteDance)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.28,"output":0.42,"cacheRead":0.056,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.28,"output":0.42,"cacheRead":0.056},"blendedRef":0.315,"blendedMin":0.315,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-6/"},{"id":"openai/gpt-oss-120b-3","name":"GPT OSS 120B (ByteDance)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.5,"cacheRead":0.02,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.5,"cacheRead":0.02},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-3/"},{"id":"zhipuai/glm-5.2-5","name":"GLM-5.2 (ByteDance)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1024000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-5/"},{"id":"bytedance/seed-1-8-251228","name":"Seed 1.8 (251228) (ByteDance)","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.05},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/bytedance/seed-1-8-251228/"},{"id":"bytedance/seed-1-6-250915","name":"Seed 1.6 (250915) (ByteDance)","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.05},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-15","lastUpdated":"2025-09-15","url":"https://llmpricing.dev/m/bytedance/seed-1-6-250915/"},{"id":"bytedance/seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715) (ByteDance)","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.07,"output":0.3,"cacheRead":0.015,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.07,"output":0.3,"cacheRead":0.015},"blendedRef":0.1275,"blendedMin":0.1275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/bytedance/seed-1-6-flash-250715/"},{"id":"bytedance/seed-1-6-250615","name":"Seed 1.6 (250615) (ByteDance)","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.05},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-25","lastUpdated":"2025-06-25","url":"https://llmpricing.dev/m/bytedance/seed-1-6-250615/"},{"id":"openai/gpt-4o-2","name":"GPT-4o (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-05-13","lastUpdated":"2024-08-06","url":"https://llmpricing.dev/m/openai/gpt-4o-2/"},{"id":"openai/gpt-5-nano-2","name":"GPT-5 Nano (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.005,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.005},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-nano-2/"},{"id":"openai/gpt-4o-mini-2","name":"GPT-4o Mini (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-2/"},{"id":"openai/gpt-3.5-turbo-2","name":"GPT-3.5 Turbo (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":16385,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-03-01","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-2/"},{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe (OpenAI)","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":16000,"contextRange":null,"outputLimit":2000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","audio"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":5,"cacheRead":null},"blendedRef":2.1875,"blendedMin":2.1875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-20","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-transcribe/"},{"id":"openai/gpt-5.5-pro-2","name":"GPT-5.5 Pro (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":30,"output":180,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":30,"output":180,"cacheRead":null},"blendedRef":67.5,"blendedMin":67.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5-pro-2/"},{"id":"openai/gpt-4-turbo-2","name":"GPT-4 Turbo (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":10,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":10,"output":30,"cacheRead":null},"blendedRef":15,"blendedMin":15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4-turbo-2/"},{"id":"openai/gpt-4-2","name":"GPT-4 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":30,"output":60,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":30,"output":60,"cacheRead":null},"blendedRef":37.5,"blendedMin":37.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4-2/"},{"id":"openai/gpt-5.6-sol-2","name":"GPT-5.6 Sol (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-2/"},{"id":"openai/gpt-5.4-pro-2","name":"GPT-5.4 Pro (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":30,"output":180,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":30,"output":180,"cacheRead":null},"blendedRef":67.5,"blendedMin":67.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-pro-2/"},{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe (OpenAI)","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":16000,"contextRange":null,"outputLimit":2000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","audio"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-20","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/openai/gpt-4o-transcribe/"},{"id":"openai/gpt-5-3","name":"GPT-5 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-3/"},{"id":"openai/gpt-5-mini-2","name":"GPT-5 Mini (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.025},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-mini-2/"},{"id":"openai/gpt-5.6-luna-2","name":"GPT-5.6 Luna (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.2,"cacheRead":0.02},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna-2/"},{"id":"openai/gpt-5.3-codex-2","name":"GPT-5.3 Codex (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/gpt-5.3-codex-2/"},{"id":"openai/gpt-4.1-nano-2","name":"GPT-4.1 Nano (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.025},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-nano-2/"},{"id":"openai/o1-3","name":"o1 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":15,"output":60,"cacheRead":7.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":15,"output":60,"cacheRead":7.5},"blendedRef":26.25,"blendedMin":26.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-05","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/openai/o1-3/"},{"id":"openai/gpt-5.2-3","name":"GPT-5.2 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-3/"},{"id":"openai/gpt-5.4-mini-2","name":"GPT-5.4 Mini (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":4.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":4.5,"cacheRead":0.075},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-mini-2/"},{"id":"openai/o3-3","name":"o3 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o3-3/"},{"id":"openai/gpt-5-pro-2","name":"GPT-5 Pro (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":272000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":15,"output":120,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":15,"output":120,"cacheRead":null},"blendedRef":41.25,"blendedMin":41.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-06","lastUpdated":"2025-10-06","url":"https://llmpricing.dev/m/openai/gpt-5-pro-2/"},{"id":"openai/gpt-5.5-2","name":"GPT-5.5 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5-2/"},{"id":"openai/gpt-4o-search-preview-2","name":"GPT-4o Search Preview (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/gpt-4o-search-preview-2/"},{"id":"openai/gpt-4.1-2","name":"GPT-4.1 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-2/"},{"id":"openai/gpt-5.6-terra-2","name":"GPT-5.6 Terra (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra-2/"},{"id":"openai/o4-mini-3","name":"o4 Mini (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.275,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.275},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-3/"},{"id":"openai/gpt-5.4-2","name":"GPT-5.4 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-2/"},{"id":"openai/o3-mini-3","name":"o3 Mini (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-20","lastUpdated":"2025-01-29","url":"https://llmpricing.dev/m/openai/o3-mini-3/"},{"id":"openai/gpt-4o-mini-search-preview-2","name":"GPT-4o Mini Search Preview (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-search-preview-2/"},{"id":"openai/gpt-5.2-pro-2","name":"GPT-5.2 Pro (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":272000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":21,"output":168,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":21,"output":168,"cacheRead":null},"blendedRef":57.75,"blendedMin":57.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-pro-2/"},{"id":"openai/gpt-4.1-mini-2","name":"GPT-4.1 Mini (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":1.6,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":1.6,"cacheRead":0.1},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-mini-2/"},{"id":"openai/gpt-5.4-nano-2","name":"GPT-5.4 Nano (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.25,"cacheRead":0.02,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.25,"cacheRead":0.02},"blendedRef":0.4625,"blendedMin":0.4625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-nano-2/"},{"id":"openai/gpt-5.1-2","name":"GPT-5.1 (OpenAI)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-2/"},{"id":"moonshotai/kimi-k3-5","name":"Kimi K3 (Together AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-5/"},{"id":"zhipuai/glm-4.7-7","name":"GLM-4.7 (Together AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.45,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.45,"output":2,"cacheRead":null},"blendedRef":0.8375,"blendedMin":0.8375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-7/"},{"id":"deepseek/deepseek-v4-flash-8","name":"DeepSeek V4 Flash (Together AI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.03},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-8/"},{"id":"deepseek/deepseek-v4-pro-7","name":"DeepSeek V4 Pro (Together AI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.32,"output":3.96,"cacheRead":0.13,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.32,"output":3.96,"cacheRead":0.13},"blendedRef":1.98,"blendedMin":1.98,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-7/"},{"id":"google/gemma-4-31b-it-5","name":"Gemma 4 31B IT (Together AI)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.39,"output":0.97,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.39,"output":0.97,"cacheRead":null},"blendedRef":0.535,"blendedMin":0.535,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-5/"},{"id":"minimax/minimax-m3","name":"MiniMax M3 (Together AI)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":524288,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/minimax/minimax-m3/"},{"id":"openai/gpt-oss-120b-4","name":"GPT OSS 120B (Together AI)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-4/"},{"id":"openai/gpt-oss-20b-3","name":"GPT OSS 20B (Together AI)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.05,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.05,"output":0.2,"cacheRead":null},"blendedRef":0.0875,"blendedMin":0.0875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-20b-3/"},{"id":"xai/grok-4-3","name":"Grok 4.3 (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/xai/grok-4-3/"},{"id":"xai/grok-4-20-beta-0309-non-reasoning","name":"Grok 4.20 Beta Non-Reasoning (0309) (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/xai/grok-4-20-beta-0309-non-reasoning/"},{"id":"xai/grok-4-6","name":"Grok 4.6 (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":null,"outputLimit":500000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.5},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/xai/grok-4-6/"},{"id":"xai/grok-4","name":"Grok 4 (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.75,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.75},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-09","url":"https://llmpricing.dev/m/xai/grok-4/"},{"id":"xai/grok-4-20-beta-0309-reasoning","name":"Grok 4.20 Beta Reasoning (0309) (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/xai/grok-4-20-beta-0309-reasoning/"},{"id":"xai/grok-4-5","name":"Grok 4.5 (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":null,"outputLimit":500000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.3},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-08","lastUpdated":"2026-07-08","url":"https://llmpricing.dev/m/xai/grok-4-5/"},{"id":"xai/grok-build-0-1","name":"Grok Build 0.1 (xAI)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1,"output":2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":2,"cacheRead":0.2},"blendedRef":1.25,"blendedMin":1.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-20","lastUpdated":"2026-05-20","url":"https://llmpricing.dev/m/xai/grok-build-0-1/"},{"id":"openai/gpt-5.6-sol-3","name":"GPT-5.6 Sol (AWS Mantle)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":278528,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5.5,"output":33,"cacheRead":0.55,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5.5,"output":33,"cacheRead":0.55},"blendedRef":12.375,"blendedMin":12.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-3/"},{"id":"openai/gpt-5.6-luna-3","name":"GPT-5.6 Luna (AWS Mantle)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":278528,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":0.22,"output":1.32,"cacheRead":0.022,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.22,"output":1.32,"cacheRead":0.022},"blendedRef":0.495,"blendedMin":0.495,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna-3/"},{"id":"openai/gpt-5.6-terra-3","name":"GPT-5.6 Terra (AWS Mantle)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":278528,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2.2,"output":13.2,"cacheRead":0.22,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.2,"output":13.2,"cacheRead":0.22},"blendedRef":4.95,"blendedMin":4.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra-3/"},{"id":"moonshotai/kimi-k2.7-code-4","name":"Kimi K2.7 Code (Nebius AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":null},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-4/"},{"id":"moonshotai/kimi-k3-6","name":"Kimi K3 (Nebius AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-6/"},{"id":"alibaba/qwen3-32b-2","name":"Qwen3 32B (Nebius AI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":40960,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-32b-2/"},{"id":"meta/llama-3.3-70b-instruct-3","name":"Llama 3.3 70B Instruct (Nebius AI)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.13,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.13,"output":0.4,"cacheRead":null},"blendedRef":0.1975,"blendedMin":0.1975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct-3/"},{"id":"nvidia/nemotron-3-nano-30b","name":"Nemotron 3 Nano 30B (Nebius AI)","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.06,"output":0.24,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2025-12-15","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-30b/"},{"id":"nvidia/nemotron-3-ultra-550b-2","name":"Nemotron 3 Ultra 550B (Nebius AI)","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":3,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-2/"},{"id":"deepseek/deepseek-v4-pro-8","name":"DeepSeek V4 Pro (Nebius AI)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.75,"output":3.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.75,"output":3.5,"cacheRead":null},"blendedRef":2.1875,"blendedMin":2.1875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-8/"},{"id":"alibaba/qwen2-5-vl-72b-instruct-2","name":"Qwen2.5 VL 72B Instruct (Nebius AI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":0.75,"cacheRead":null},"blendedRef":0.375,"blendedMin":0.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/alibaba/qwen2-5-vl-72b-instruct-2/"},{"id":"minimax/minimax-m3-2","name":"MiniMax M3 (Nebius AI)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/minimax/minimax-m3-2/"},{"id":"nebius/cosmos3-super-reasoner","name":"Cosmos 3 Super Reasoner (Nebius AI)","lab":"nebius","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/nebius/cosmos3-super-reasoner/"},{"id":"nebius/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507 (Nebius AI)","lab":"nebius","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-30","lastUpdated":"2025-07-30","url":"https://llmpricing.dev/m/nebius/qwen3-30b-a3b-instruct-2507/"},{"id":"openai/gpt-oss-120b-5","name":"GPT OSS 120B (Nebius AI)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-5/"},{"id":"nvidia/nemotron-3-super-120b","name":"Nemotron 3 Super 120B (Nebius AI)","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b/"},{"id":"nebius/hermes-4-70b","name":"Hermes 4 70B (Nebius AI)","lab":"nebius","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.13,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.13,"output":0.4,"cacheRead":null},"blendedRef":0.1975,"blendedMin":0.1975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/nebius/hermes-4-70b/"},{"id":"nebius/minicpm-v-4.5","name":"MiniCPM-V 4.5 (Nebius AI)","lab":"nebius","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.658,"output":1.11,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.658,"output":1.11,"cacheRead":null},"blendedRef":0.771,"blendedMin":0.771,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/nebius/minicpm-v-4.5/"},{"id":"alibaba/qwen3-next-80b-a3b-thinking-2","name":"Qwen3 Next 80B A3B Thinking (Nebius AI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":1.2,"cacheRead":null},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09","lastUpdated":"2025-09","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-thinking-2/"},{"id":"nebius/hermes-4-405b","name":"Hermes 4 405B (Nebius AI)","lab":"nebius","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":3,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/nebius/hermes-4-405b/"},{"id":"zhipuai/glm-5.2-6","name":"GLM-5.2 (Nebius AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":null},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-6/"},{"id":"minimax/minimax-m2.5-3","name":"MiniMax M2.5 (Nebius AI)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":196608,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-3/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507-4","name":"Qwen3 235B A22B Instruct 2507 (Nebius AI)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.6,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-07-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507-4/"},{"id":"nvidia/nemotron-3-nano-omni-2","name":"Nemotron 3 Nano Omni (Nebius AI)","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.06,"output":0.24,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-28","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni-2/"},{"id":"google/gemma-3-27b","name":"Gemma 3 27B (Nebius AI)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":110000,"contextRange":null,"outputLimit":110000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/google/gemma-3-27b/"},{"id":"zhipuai/glm-5.1-6","name":"GLM-5.1 (Nebius AI)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":null},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-6/"},{"id":"nvidia/llama-3.1-nemotron-ultra-253b-2","name":"Llama 3.1 Nemotron Ultra 253B (Nebius AI)","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":1.8,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":1.8,"cacheRead":null},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-07","lastUpdated":"2025-04-07","url":"https://llmpricing.dev/m/nvidia/llama-3.1-nemotron-ultra-253b-2/"},{"id":"moonshotai/kimi-k2.6-5","name":"Kimi K2.6 (Nebius AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":null},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-5/"},{"id":"google/gemini-3.5-flash-lite-3","name":"Gemini 3.5 Flash Lite (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-lite-3/"},{"id":"google/gemini-3.1-pro-preview-4","name":"Gemini 3.1 Pro (Preview) (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-4/"},{"id":"google/gemini-2.5-flash-lite-3","name":"Gemini 2.5 Flash Lite (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.01},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-3/"},{"id":"google/gemini-3.5-flash-3","name":"Gemini 3.5 Flash (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":1.5,"output":9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.5,"output":9,"cacheRead":0.15},"blendedRef":3.375,"blendedMin":3.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-3/"},{"id":"google/gemini-3.1-flash-lite-3","name":"Gemini 3.1 Flash Lite (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":1.5,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite-3/"},{"id":"google/gemini-2.5-flash-3","name":"Gemini 2.5 Flash (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-3/"},{"id":"google/gemini-3.6-flash-3","name":"Gemini 3.6 Flash (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.6-flash-3/"},{"id":"google/gemini-pro-latest-3","name":"Gemini Pro Latest (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-27","lastUpdated":"2026-02-27","url":"https://llmpricing.dev/m/google/gemini-pro-latest-3/"},{"id":"google/gemini-3-flash-preview-3","name":"Gemini 3 Flash (Preview) (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-17","lastUpdated":"2025-12-17","url":"https://llmpricing.dev/m/google/gemini-3-flash-preview-3/"},{"id":"google/gemini-2.5-pro-3","name":"Gemini 2.5 Pro (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-3/"},{"id":"google/gemini-3.7-flash-3","name":"Gemini 3.7 Flash (Google AI Studio)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-13","lastUpdated":"2026-08-13","url":"https://llmpricing.dev/m/google/gemini-3.7-flash-3/"},{"id":"anthropic/claude-opus-4-7-3","name":"Claude Opus 4.7 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-7-3/"},{"id":"xai/grok-4-3-2","name":"Grok 4.3 (AWS Bedrock)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/xai/grok-4-3-2/"},{"id":"anthropic/claude-opus-4-1-20250805-3","name":"Claude Opus 4.1 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-20250805-3/"},{"id":"anthropic/claude-opus-4-8-3","name":"Claude Opus 4.8 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-8-3/"},{"id":"meta/llama-4-scout-17b-instruct-3","name":"Llama 4 Scout 17B Instruct (AWS Bedrock)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.17,"output":0.66,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.17,"output":0.66,"cacheRead":null},"blendedRef":0.2925,"blendedMin":0.2925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-instruct-3/"},{"id":"anthropic/claude-sonnet-5-3","name":"Claude Sonnet 5 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-5-3/"},{"id":"xai/grok-4-6-2","name":"Grok 4.6 (AWS Bedrock)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":null,"outputLimit":500000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.5},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/xai/grok-4-6-2/"},{"id":"anthropic/claude-sonnet-4-5-20250929-4","name":"Claude Sonnet 4.5 (2025-09-29) (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-20250929-4/"},{"id":"meta/llama-3.1-70b-instruct-2","name":"Llama 3.1 70B Instruct (AWS Bedrock)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.72,"output":0.72,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.72,"output":0.72,"cacheRead":null},"blendedRef":0.72,"blendedMin":0.72,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-70b-instruct-2/"},{"id":"anthropic/claude-sonnet-4-6-3","name":"Claude Sonnet 4.6 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-6-3/"},{"id":"anthropic/claude-haiku-4-5-20251001-4","name":"Claude Haiku 4.5 (2025-10-01) (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-20251001-4/"},{"id":"anthropic/claude-sonnet-4-5-3","name":"Claude Sonnet 4.5 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-3/"},{"id":"anthropic/claude-opus-4-5-20251101-4","name":"Claude Opus 4.5 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2025-11-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-20251101-4/"},{"id":"anthropic/claude-fable-5-3","name":"Claude Fable 5 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/claude-fable-5-3/"},{"id":"meta/llama-4-maverick-17b-instruct-3","name":"Llama 4 Maverick 17B Instruct (AWS Bedrock)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.24,"output":0.97,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.24,"output":0.97,"cacheRead":null},"blendedRef":0.4225,"blendedMin":0.4225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-instruct-3/"},{"id":"anthropic/claude-haiku-4-5-3","name":"Claude Haiku 4.5 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-3/"},{"id":"anthropic/claude-opus-4-6-3","name":"Claude Opus 4.6 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-6-3/"},{"id":"anthropic/claude-opus-5-3","name":"Claude Opus 5 (AWS Bedrock)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/claude-opus-5-3/"},{"id":"moonshotai/kimi-k3-7","name":"Kimi K3 (CanopyWave)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-7/"},{"id":"deepseek/deepseek-v4-flash-9","name":"DeepSeek V4 Flash (CanopyWave)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.03},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-9/"},{"id":"deepseek/deepseek-v4-pro-9","name":"DeepSeek V4 Pro (CanopyWave)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.74,"output":3.48,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.74,"output":3.48,"cacheRead":0.01},"blendedRef":2.175,"blendedMin":2.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-9/"},{"id":"zhipuai/glm-5.2-7","name":"GLM-5.2 (CanopyWave)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-7/"},{"id":"moonshotai/kimi-k2.6-6","name":"Kimi K2.6 (CanopyWave)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.16,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.16},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-6/"},{"id":"zhipuai/glm-5.2-fast-2","name":"GLM-5.2 Turbo (SCX.ai)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.99,"output":6.16,"cacheRead":0.4,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.99,"output":6.16,"cacheRead":0.4},"blendedRef":3.0325,"blendedMin":3.0325,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-fast-2/"},{"id":"alibaba/qwen3.8-max-3","name":"Qwen3.8 Max (SCX.ai)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"llmgateway-providers","input":1.815,"output":5.4461,"cacheRead":0.21,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.815,"output":5.4461,"cacheRead":0.21},"blendedRef":2.7228,"blendedMin":2.7228,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-03","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/alibaba/qwen3.8-max-3/"},{"id":"zhipuai/glm-5.2-8","name":"GLM-5.2 (SCX.ai)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.55,"output":1.784,"cacheRead":0.111,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.55,"output":1.784,"cacheRead":0.111},"blendedRef":0.8585,"blendedMin":0.8585,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-8/"},{"id":"xiaomi/mimo-v2.5-2","name":"MiMo V2.5 (Xiaomi)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.0028,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-2/"},{"id":"xiaomi/mimo-v2.5-pro-2","name":"MiMo V2.5 Pro (Xiaomi)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.435,"output":0.87,"cacheRead":0.0036,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.435,"output":0.87,"cacheRead":0.0036},"blendedRef":0.5438,"blendedMin":0.5438,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-pro-2/"},{"id":"alibaba/qwen3-vl-plus-2","name":"Qwen3 VL Plus (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.6,"cacheRead":0.04,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.6,"cacheRead":0.04},"blendedRef":0.55,"blendedMin":0.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-plus-2/"},{"id":"alibaba/qwen3.7-max-3","name":"Qwen3.7 Max (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":7.5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":7.5,"cacheRead":0.5},"blendedRef":3.75,"blendedMin":3.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-21","lastUpdated":"2026-05-21","url":"https://llmpricing.dev/m/alibaba/qwen3.7-max-3/"},{"id":"alibaba/qwen-omni-turbo-2","name":"Qwen Omni Turbo (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-19","lastUpdated":"2025-03-26","url":"https://llmpricing.dev/m/alibaba/qwen-omni-turbo-2/"},{"id":"deepseek/deepseek-v4-flash-10","name":"DeepSeek V4 Flash (Alibaba Cloud)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.4,"cacheRead":0.04,"official":false},"cheapest":{"provider":"aihubmix","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.25,"blendedMin":0.175,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-10/"},{"id":"alibaba/qwen-max-3","name":"Qwen Max (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.6,"output":6.4,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.6,"output":6.4,"cacheRead":null},"blendedRef":2.8,"blendedMin":2.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-03","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-max-3/"},{"id":"alibaba/qwen-plus-2","name":"Qwen Plus (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":1.2,"cacheRead":0.08,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":1.2,"cacheRead":0.08},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2025-09-11","url":"https://llmpricing.dev/m/alibaba/qwen-plus-2/"},{"id":"deepseek/deepseek-v4-pro-10","name":"DeepSeek V4 Pro (Alibaba Cloud)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":393216,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":2.4,"output":4.8,"cacheRead":0.2,"official":false},"cheapest":{"provider":"aihubmix","input":1.69,"output":3.38,"cacheRead":0.13},"blendedRef":3,"blendedMin":2.1125,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-10/"},{"id":"alibaba/qwen3-coder-flash-2","name":"Qwen3 Coder Flash (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.5,"cacheRead":0.06},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-flash-2/"},{"id":"alibaba/qwen-plus-latest","name":"Qwen Plus Latest (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":1.2,"cacheRead":0.08,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":1.2,"cacheRead":0.08},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-09","lastUpdated":"2024-09-09","url":"https://llmpricing.dev/m/alibaba/qwen-plus-latest/"},{"id":"zhipuai/glm-5-5","name":"GLM-5 (Alibaba Cloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.573,"output":2.58,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.573,"output":2.58,"cacheRead":null},"blendedRef":1.0747,"blendedMin":1.0747,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-5/"},{"id":"alibaba/qwen3.6-max-preview-2","name":"Qwen3.6 Max Preview (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.3,"output":7.8,"cacheRead":0.13,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.3,"output":7.8,"cacheRead":0.13},"blendedRef":2.925,"blendedMin":2.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-20","lastUpdated":"2026-04-20","url":"https://llmpricing.dev/m/alibaba/qwen3.6-max-preview-2/"},{"id":"alibaba/qwen3.8-max-4","name":"Qwen3.8 Max (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":6,"cacheRead":0.25},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-03","lastUpdated":"2026-08-03","url":"https://llmpricing.dev/m/alibaba/qwen3.8-max-4/"},{"id":"alibaba/qwen3.7-plus-2","name":"Qwen3.7 Plus (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":1.6,"cacheRead":0.08,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":1.6,"cacheRead":0.08},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-02","url":"https://llmpricing.dev/m/alibaba/qwen3.7-plus-2/"},{"id":"alibaba/qwen35-397b-a17b-2","name":"Qwen3.5 397B A17B (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":3.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":3.6,"cacheRead":null},"blendedRef":1.35,"blendedMin":1.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen35-397b-a17b-2/"},{"id":"alibaba/qwen3.7-flash-2","name":"Qwen3.7 Flash (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.03,"output":0.13,"cacheRead":0.006,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.03,"output":0.13,"cacheRead":0.006},"blendedRef":0.055,"blendedMin":0.055,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-15","lastUpdated":"2026-07-15","url":"https://llmpricing.dev/m/alibaba/qwen3.7-flash-2/"},{"id":"moonshotai/kimi-k2.5-6","name":"Kimi K2.5 (Alibaba Cloud)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.574,"output":3.011,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.574,"output":3.011,"cacheRead":null},"blendedRef":1.1833,"blendedMin":1.1833,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-6/"},{"id":"alibaba/qwen-flash-2","name":"Qwen Flash (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.01},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/alibaba/qwen-flash-2/"},{"id":"alibaba/qwen3-max-3","name":"Qwen3 Max (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32800,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.6,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.6},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/alibaba/qwen3-max-3/"},{"id":"zhipuai/glm-5.2-9","name":"GLM-5.2 (Alibaba Cloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.28,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.28},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-9/"},{"id":"alibaba/qwen3.6-35b-a3b-4","name":"Qwen3.6 35B A3B (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"llmgateway-providers","input":0.248,"output":1.485,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.248,"output":1.485,"cacheRead":null},"blendedRef":0.5573,"blendedMin":0.5573,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-4/"},{"id":"alibaba/qwen3.6-plus-2","name":"Qwen3.6 Plus (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/alibaba/qwen3.6-plus-2/"},{"id":"alibaba/qwen-coder-plus","name":"Qwen Coder Plus (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.502,"output":1.004,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.502,"output":1.004,"cacheRead":null},"blendedRef":0.6275,"blendedMin":0.6275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-18","lastUpdated":"2024-09-18","url":"https://llmpricing.dev/m/alibaba/qwen-coder-plus/"},{"id":"alibaba/qwen3-coder-plus-2","name":"Qwen3 Coder Plus (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":66000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":6,"output":60,"cacheRead":1.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":6,"output":60,"cacheRead":1.2},"blendedRef":19.5,"blendedMin":19.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-plus-2/"},{"id":"alibaba/qwen3-vl-flash","name":"Qwen3 VL Flash (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.01},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-flash/"},{"id":"alibaba/qwen3.6-flash-2","name":"Qwen3.6 Flash (Alibaba Cloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":1.5,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":1.5,"cacheRead":0.05},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/alibaba/qwen3.6-flash-2/"},{"id":"sakana/fugu-ultra-2","name":"Fugu Ultra (Sakana AI)","lab":"sakana","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-15","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/sakana/fugu-ultra-2/"},{"id":"meta/llama-3.2-11b-instruct","name":"Llama 3.2 11B Instruct (Inference.net)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.07,"output":0.33,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.07,"output":0.33,"cacheRead":null},"blendedRef":0.135,"blendedMin":0.135,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-11b-instruct/"},{"id":"moonshotai/kimi-k3-8","name":"Kimi K3 (Permafrost)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.6,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.6},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-8/"},{"id":"perplexity/sonar-3","name":"Sonar (Perplexity)","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":130000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":1,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-3/"},{"id":"perplexity/sonar-reasoning-pro-3","name":"Sonar Reasoning Pro (Perplexity)","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-reasoning-pro-3/"},{"id":"perplexity/sonar-pro-3","name":"Sonar Pro (Perplexity)","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-pro-3/"},{"id":"moonshotai/kimi-k2.6-7","name":"Kimi K2.6 (Tundra)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":2.2,"cacheRead":0.08,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":2.2,"cacheRead":0.08},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-7/"},{"id":"alibaba/qwen3-32b-3","name":"Qwen3 32B (SCX.ai (Turbo))","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.36,"output":0.87,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.36,"output":0.87,"cacheRead":null},"blendedRef":0.4875,"blendedMin":0.4875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-32b-3/"},{"id":"google/gemma-4-31b-it-6","name":"Gemma 4 31B IT (SCX.ai (Turbo))","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":0.91,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":0.91,"cacheRead":null},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-6/"},{"id":"minimax/minimax-m2.7-2","name":"MiniMax M2.7 (SCX.ai (Turbo))","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":196608,"contextRange":null,"outputLimit":196608,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.48,"output":1.79,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.48,"output":1.79,"cacheRead":0.05},"blendedRef":0.8075,"blendedMin":0.8075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/minimax-m2.7-2/"},{"id":"openai/gpt-oss-120b-6","name":"GPT OSS 120B (SCX.ai (Turbo))","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.17,"output":0.55,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.17,"output":0.55,"cacheRead":null},"blendedRef":0.265,"blendedMin":0.265,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-6/"},{"id":"meta/llama-4-maverick-17b-instruct-4","name":"Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.53,"output":1.62,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.53,"output":1.62,"cacheRead":null},"blendedRef":0.8025,"blendedMin":0.8025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-instruct-4/"},{"id":"xai/grok-4-3-3","name":"Grok 4.3 (Azure AI Foundry)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":20000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/xai/grok-4-3-3/"},{"id":"xai/grok-4-1-fast-reasoning-2","name":"Grok 4.1 Fast Reasoning (Azure AI Foundry)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.5,"cacheRead":null},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-19","lastUpdated":"2025-11-19","url":"https://llmpricing.dev/m/xai/grok-4-1-fast-reasoning-2/"},{"id":"xai/grok-4-1-fast-non-reasoning-2","name":"Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.5,"cacheRead":null},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-19","lastUpdated":"2025-11-19","url":"https://llmpricing.dev/m/xai/grok-4-1-fast-non-reasoning-2/"},{"id":"moonshotai/kimi-k2.7-code-5","name":"Kimi K2.7 Code (Moonshot AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.19,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.19},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-5/"},{"id":"moonshotai/kimi-k3-9","name":"Kimi K3 (Moonshot AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-9/"},{"id":"moonshotai/kimi-k2.5-7","name":"Kimi K2.5 (Moonshot AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":3,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":3,"cacheRead":0.1},"blendedRef":1.2,"blendedMin":1.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-7/"},{"id":"moonshotai/kimi-k2.7-code-highspeed-2","name":"Kimi K2.7 Code Highspeed (Moonshot AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":1.9,"output":8,"cacheRead":0.38,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.9,"output":8,"cacheRead":0.38},"blendedRef":3.425,"blendedMin":3.425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-highspeed-2/"},{"id":"moonshotai/kimi-k2.6-8","name":"Kimi K2.6 (Moonshot AI)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.16,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.16},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-8/"},{"id":"openai/gpt-4o-3","name":"GPT-4o (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-05-13","lastUpdated":"2024-08-06","url":"https://llmpricing.dev/m/openai/gpt-4o-3/"},{"id":"openai/gpt-5-nano-3","name":"GPT-5 Nano (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.005,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.05,"output":0.4,"cacheRead":0.005},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-nano-3/"},{"id":"openai/gpt-3.5-turbo-3","name":"GPT-3.5 Turbo (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":16385,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-03-01","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-3/"},{"id":"openai/gpt-4-turbo-3","name":"GPT-4 Turbo (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":10,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":10,"output":30,"cacheRead":null},"blendedRef":15,"blendedMin":15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4-turbo-3/"},{"id":"openai/gpt-4-3","name":"GPT-4 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":30,"output":60,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":30,"output":60,"cacheRead":null},"blendedRef":37.5,"blendedMin":37.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4-3/"},{"id":"openai/gpt-5.6-sol-4","name":"GPT-5.6 Sol (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-4/"},{"id":"openai/gpt-5.4-pro-3","name":"GPT-5.4 Pro (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":30,"output":180,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":30,"output":180,"cacheRead":null},"blendedRef":67.5,"blendedMin":67.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-pro-3/"},{"id":"openai/gpt-5-4","name":"GPT-5 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-4/"},{"id":"openai/gpt-5.1-codex-mini-2","name":"GPT-5.1 Codex mini (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.025},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex-mini-2/"},{"id":"openai/gpt-5-mini-3","name":"GPT-5 Mini (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.25,"output":2,"cacheRead":0.025},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-mini-3/"},{"id":"openai/gpt-5.6-luna-4","name":"GPT-5.6 Luna (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.2,"cacheRead":0.02},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna-4/"},{"id":"openai/gpt-5.3-codex-3","name":"GPT-5.3 Codex (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/gpt-5.3-codex-3/"},{"id":"openai/gpt-oss-120b-7","name":"GPT OSS 120B (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-7/"},{"id":"openai/gpt-4.1-nano-3","name":"GPT-4.1 Nano (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.4,"cacheRead":0.025},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-nano-3/"},{"id":"openai/o1-4","name":"o1 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":15,"output":60,"cacheRead":7.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":15,"output":60,"cacheRead":7.5},"blendedRef":26.25,"blendedMin":26.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-05","lastUpdated":"2024-12-05","url":"https://llmpricing.dev/m/openai/o1-4/"},{"id":"openai/gpt-5.2-4","name":"GPT-5.2 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-4/"},{"id":"openai/gpt-5.4-mini-3","name":"GPT-5.4 Mini (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":4.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":4.5,"cacheRead":0.075},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-mini-3/"},{"id":"openai/o3-4","name":"o3 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o3-4/"},{"id":"openai/gpt-5.5-3","name":"GPT-5.5 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5-3/"},{"id":"openai/gpt-5.2-codex-2","name":"GPT-5.2 Codex (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-codex-2/"},{"id":"openai/gpt-4.1-3","name":"GPT-4.1 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":8,"cacheRead":0.5},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-3/"},{"id":"openai/gpt-5.6-terra-4","name":"GPT-5.6 Terra (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra-4/"},{"id":"openai/o4-mini-4","name":"o4 Mini (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.275,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.275},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-4/"},{"id":"openai/gpt-5.4-3","name":"GPT-5.4 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-3/"},{"id":"openai/o3-mini-4","name":"o3 Mini (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-20","lastUpdated":"2025-01-29","url":"https://llmpricing.dev/m/openai/o3-mini-4/"},{"id":"openai/gpt-5.2-pro-3","name":"GPT-5.2 Pro (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":272000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":21,"output":168,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":21,"output":168,"cacheRead":null},"blendedRef":57.75,"blendedMin":57.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-pro-3/"},{"id":"openai/gpt-5.1-codex-2","name":"GPT-5.1 Codex (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":272000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":null},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex-2/"},{"id":"openai/gpt-4.1-mini-3","name":"GPT-4.1 Mini (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":1.6,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":1.6,"cacheRead":0.1},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-mini-3/"},{"id":"openai/gpt-5.4-nano-3","name":"GPT-5.4 Nano (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.25,"cacheRead":0.02,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.25,"cacheRead":0.02},"blendedRef":0.4625,"blendedMin":0.4625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-nano-3/"},{"id":"openai/gpt-5.1-3","name":"GPT-5.1 (Azure)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-3/"},{"id":"deepseek/deepseek-v4-flash-11","name":"DeepSeek V4 Flash (Runware)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.076,"output":0.153,"cacheRead":0.014,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.076,"output":0.153,"cacheRead":0.014},"blendedRef":0.0953,"blendedMin":0.0953,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-11/"},{"id":"deepseek/deepseek-v4-pro-11","name":"DeepSeek V4 Pro (Runware)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.961,"output":1.922,"cacheRead":0.079,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.961,"output":1.922,"cacheRead":0.079},"blendedRef":1.2013,"blendedMin":1.2013,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-11/"},{"id":"google/gemma-4-31b-it-7","name":"Gemma 4 31B IT (Runware)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.102,"output":0.297,"cacheRead":0.012,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.102,"output":0.297,"cacheRead":0.012},"blendedRef":0.1508,"blendedMin":0.1508,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-7/"},{"id":"openai/gpt-oss-120b-8","name":"GPT OSS 120B (Runware)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.032,"output":0.14,"cacheRead":0.032,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.032,"output":0.14,"cacheRead":0.032},"blendedRef":0.059,"blendedMin":0.059,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-8/"},{"id":"zhipuai/glm-5.2-10","name":"GLM-5.2 (Runware)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1024000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.8,"output":2.55,"cacheRead":0.16,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.8,"output":2.55,"cacheRead":0.16},"blendedRef":1.2375,"blendedMin":1.2375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-10/"},{"id":"moonshotai/kimi-k2.6-9","name":"Kimi K2.6 (Runware)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":3.05,"cacheRead":0.13,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":3.05,"cacheRead":0.13},"blendedRef":1.2125,"blendedMin":1.2125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-9/"},{"id":"google/gemini-3.1-pro-preview-5","name":"Gemini 3.1 Pro (Preview) (Iceberg)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro-preview-5/"},{"id":"google/gemini-3.6-flash-4","name":"Gemini 3.6 Flash (Iceberg)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.6-flash-4/"},{"id":"google/gemini-3-flash-preview-4","name":"Gemini 3 Flash (Preview) (Iceberg)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":3,"cacheRead":0.05},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-17","lastUpdated":"2025-12-17","url":"https://llmpricing.dev/m/google/gemini-3-flash-preview-4/"},{"id":"mistral/ministral-8b-2512-3","name":"Ministral 8B (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-8b-2512-3/"},{"id":"mistral/mistral-large-latest-2","name":"Mistral Large Latest (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":4,"output":12,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":4,"output":12,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral-large-latest-2/"},{"id":"mistral/devstral-2512-2","name":"Devstral 2 (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.4,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.4,"output":2,"cacheRead":null},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-09","lastUpdated":"2025-12-09","url":"https://llmpricing.dev/m/mistral/devstral-2512-2/"},{"id":"mistral/mistral-small-2506-2","name":"Mistral Small 3.2 (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2025-06-20","url":"https://llmpricing.dev/m/mistral/mistral-small-2506-2/"},{"id":"mistral/mistral-large-2512-2","name":"Mistral Large 3 (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.5,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/mistral-large-2512-2/"},{"id":"mistral/ministral-3b-2512-3","name":"Ministral 3B (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-3b-2512-3/"},{"id":"mistral/ministral-14b-2512-3","name":"Ministral 14B (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":0.2,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-14b-2512-3/"},{"id":"mistral/codestral-2508-2","name":"Codestral (Mistral AI)","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":0.9,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-30","lastUpdated":"2025-07-30","url":"https://llmpricing.dev/m/mistral/codestral-2508-2/"},{"id":"zhipuai/glm-4.7-8","name":"GLM-4.7 (Vertex AI (OpenAI-compatible))","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-8/"},{"id":"deepseek/deepseek-v3.2-7","name":"DeepSeek V3.2 (Vertex AI (OpenAI-compatible))","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.56,"output":1.68,"cacheRead":0.056,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.56,"output":1.68,"cacheRead":0.056},"blendedRef":0.84,"blendedMin":0.84,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-7/"},{"id":"zhipuai/glm-5-6","name":"GLM-5 (Vertex AI (OpenAI-compatible))","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.1},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-6/"},{"id":"alibaba/qwen3-next-80b-a3b-thinking-3","name":"Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":1.2,"cacheRead":null},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09","lastUpdated":"2025-09","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-thinking-3/"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct-3","name":"Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible))","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.22,"output":1.8,"cacheRead":0.022,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.22,"output":1.8,"cacheRead":0.022},"blendedRef":0.615,"blendedMin":0.615,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-480b-a35b-instruct-3/"},{"id":"xai/grok-4-20-reasoning","name":"Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/xai/grok-4-20-reasoning/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507-5","name":"Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.22,"output":0.88,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.22,"output":0.88,"cacheRead":null},"blendedRef":0.385,"blendedMin":0.385,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-07-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507-5/"},{"id":"alibaba/qwen3-next-80b-a3b-instruct-3","name":"Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":1.2,"cacheRead":null},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09","lastUpdated":"2025-09","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-instruct-3/"},{"id":"xai/grok-4-20-non-reasoning","name":"Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/xai/grok-4-20-non-reasoning/"},{"id":"moonshotai/kimi-k2-thinking-3","name":"Kimi K2 Thinking (Vertex AI (OpenAI-compatible))","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.5,"cacheRead":0.06},"blendedRef":1.075,"blendedMin":1.075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-06","lastUpdated":"2025-11-06","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-thinking-3/"},{"id":"zhipuai/glm-4.7-9","name":"GLM-4.7 (Cerebras)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":2.25,"output":2.75,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2.25,"output":2.75,"cacheRead":null},"blendedRef":2.375,"blendedMin":2.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-9/"},{"id":"meta/llama-3.3-70b-instruct-4","name":"Llama 3.3 70B Instruct (Cerebras)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.85,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.85,"output":1.2,"cacheRead":null},"blendedRef":0.9375,"blendedMin":0.9375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-instruct-4/"},{"id":"google/gemma-4-31b-it-8","name":"Gemma 4 31B IT (Cerebras)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway-providers","input":0.99,"output":1.49,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.99,"output":1.49,"cacheRead":null},"blendedRef":1.115,"blendedMin":1.115,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-8/"},{"id":"openai/gpt-oss-120b-9","name":"GPT OSS 120B (Cerebras)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.35,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.35,"output":0.75,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-9/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507-6","name":"Qwen3 235B A22B Instruct 2507 (Cerebras)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":1.2,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-07-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507-6/"},{"id":"deepseek/deepseek-v4-flash-12","name":"DeepSeek V4 Flash (Baidu)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.028,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.14,"output":0.28,"cacheRead":0.028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-12/"},{"id":"deepseek/deepseek-v4-pro-12","name":"DeepSeek V4 Pro (Baidu)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.69,"output":3.38,"cacheRead":0.14,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.69,"output":3.38,"cacheRead":0.14},"blendedRef":2.1125,"blendedMin":2.1125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-12/"},{"id":"zhipuai/glm-5-7","name":"GLM-5 (Baidu)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":3.2,"cacheRead":0.2},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-7/"},{"id":"zhipuai/glm-5.2-11","name":"GLM-5.2 (Baidu)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-11/"},{"id":"zhipuai/glm-5.1-7","name":"GLM-5.1 (Baidu)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-7/"},{"id":"moonshotai/kimi-k2.6-10","name":"Kimi K2.6 (Baidu)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.16,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.95,"output":4,"cacheRead":0.16},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-10/"},{"id":"zhipuai/glm-4.7-10","name":"GLM-4.7 (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.38,"output":1.98,"cacheRead":0.19,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.38,"output":1.98,"cacheRead":0.19},"blendedRef":0.78,"blendedMin":0.78,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-10/"},{"id":"alibaba/qwen3-coder-next-3","name":"Qwen3 Coder Next (EmberCloud)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.108,"output":0.675,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.108,"output":0.675,"cacheRead":0.06},"blendedRef":0.2498,"blendedMin":0.2498,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-03","lastUpdated":"2026-02-03","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-next-3/"},{"id":"zhipuai/glm-5-8","name":"GLM-5 (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":203000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.72,"output":2.3,"cacheRead":0.144,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.72,"output":2.3,"cacheRead":0.144},"blendedRef":1.115,"blendedMin":1.115,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-8/"},{"id":"moonshotai/kimi-k2.5-8","name":"Kimi K2.5 (EmberCloud)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.405,"output":1.98,"cacheRead":0.225,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.405,"output":1.98,"cacheRead":0.225},"blendedRef":0.7988,"blendedMin":0.7988,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01","lastUpdated":"2026-01","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-8/"},{"id":"zhipuai/glm-5.2-12","name":"GLM-5.2 (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":203000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":1.26,"output":3.96,"cacheRead":0.234,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1.26,"output":3.96,"cacheRead":0.234},"blendedRef":1.935,"blendedMin":1.935,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-12/"},{"id":"zhipuai/glm-4.5-air-3","name":"GLM-4.5 Air (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":null,"outputLimit":96000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.13,"output":0.85,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.13,"output":0.85,"cacheRead":0.025},"blendedRef":0.31,"blendedMin":0.31,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-air-3/"},{"id":"zhipuai/glm-5.1-8","name":"GLM-5.1 (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":203000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.931,"output":2.93,"cacheRead":0.173,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.931,"output":2.93,"cacheRead":0.173},"blendedRef":1.4308,"blendedMin":1.4308,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-8/"},{"id":"zhipuai/glm-4.7-flash-2","name":"GLM-4.7 Flash (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.06,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.06,"output":0.4,"cacheRead":0.01},"blendedRef":0.145,"blendedMin":0.145,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-flash-2/"},{"id":"zhipuai/glm-4.5-3","name":"GLM-4.5 (EmberCloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":null,"outputLimit":96000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.2,"cacheRead":0.11},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-3/"},{"id":"openai/gpt-oss-120b-10","name":"GPT OSS 120B (Groq)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32766,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.15,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.15,"output":0.75,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-10/"},{"id":"openai/gpt-oss-20b-4","name":"GPT OSS 20B (Groq)","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32766,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.1,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.1,"output":0.5,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-20b-4/"},{"id":"deepseek/deepseek-v4-flash-13","name":"DeepSeek V4 Flash (Gonka24)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":390000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.075,"output":0.175,"cacheRead":0.0155,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.075,"output":0.175,"cacheRead":0.0155},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-13/"},{"id":"minimax/minimax-m2.7-3","name":"MiniMax M2.7 (Gonka24)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.08,"output":0.32,"cacheRead":0.017,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.08,"output":0.32,"cacheRead":0.017},"blendedRef":0.14,"blendedMin":0.14,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/minimax-m2.7-3/"},{"id":"moonshotai/kimi-k2.6-11","name":"Kimi K2.6 (Gonka24)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":98304,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.22,"output":1.137,"cacheRead":0.048,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.22,"output":1.137,"cacheRead":0.048},"blendedRef":0.4493,"blendedMin":0.4493,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-11/"},{"id":"anthropic/claude-opus-4-7-4","name":"Claude Opus 4.7 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-7-4/"},{"id":"anthropic/claude-sonnet-5-4","name":"Claude Sonnet 5 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"llmgateway-providers","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-5-4/"},{"id":"anthropic/claude-sonnet-4-6-4","name":"Claude Sonnet 4.6 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-6-4/"},{"id":"anthropic/claude-sonnet-4-5-4","name":"Claude Sonnet 4.5 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"llmgateway-providers","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-4/"},{"id":"anthropic/claude-opus-4-5-20251101-5","name":"Claude Opus 4.5 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-01","lastUpdated":"2025-11-01","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-20251101-5/"},{"id":"anthropic/claude-haiku-4-5-4","name":"Claude Haiku 4.5 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"llmgateway-providers","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-4/"},{"id":"anthropic/claude-opus-4-6-4","name":"Claude Opus 4.6 (Vertex AI (Anthropic))","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmgateway-providers","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-6-4/"},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 Highspeed (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.4,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.4,"cacheRead":0.06},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/minimax-m2.7-highspeed/"},{"id":"minimax/minimax-text-01","name":"MiniMax Text 01 (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1.1,"cacheRead":null},"blendedRef":0.425,"blendedMin":0.425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-15","lastUpdated":"2025-01-15","url":"https://llmpricing.dev/m/minimax/minimax-text-01/"},{"id":"minimax/minimax-m2.5-highspeed-2","name":"MiniMax M2.5 Highspeed (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.4,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.4,"cacheRead":0.03},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-13","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-highspeed-2/"},{"id":"minimax/minimax-m3-3","name":"MiniMax M3 (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":512000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway-providers","input":0.6,"output":2.4,"cacheRead":0.12,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.6,"output":2.4,"cacheRead":0.12},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/minimax/minimax-m3-3/"},{"id":"minimax/minimax-m2.7-4","name":"MiniMax M2.7 (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/minimax-m2.7-4/"},{"id":"minimax/minimax-m2-2","name":"MiniMax M2 (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":196608,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.2,"output":1,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.2,"output":1,"cacheRead":0.03},"blendedRef":0.4,"blendedMin":0.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-27","lastUpdated":"2025-10-27","url":"https://llmpricing.dev/m/minimax/minimax-m2-2/"},{"id":"minimax/minimax-m2.5-4","name":"MiniMax M2.5 (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-4/"},{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":196608,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.12,"output":0.48,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.12,"output":0.48,"cacheRead":null},"blendedRef":0.21,"blendedMin":0.21,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/minimax-m2.1-lightning/"},{"id":"minimax/minimax-m2.1-3","name":"MiniMax M2.1 (MiniMax)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":196608,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway-providers","input":0.27,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway-providers","input":0.27,"output":1.1,"cacheRead":null},"blendedRef":0.4775,"blendedMin":0.4775,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/minimax-m2.1-3/"},{"id":"minimax/minimax-m2.5-fast","name":"MiniMax-M2.5-fast","lab":"minimax","kind":"text","status":"deprecated","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.3,"output":1.2,"cacheRead":0.03,"official":false},"cheapest":{"provider":"nebius","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":0.525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-20","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-fast/"},{"id":"openai/gpt-oss-120b-fast","name":"gpt-oss-120b-fast","lab":"openai","kind":"text","status":"deprecated","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.1,"output":0.5,"cacheRead":0.01,"official":false},"cheapest":{"provider":"nebius","input":0.1,"output":0.5,"cacheRead":0.01},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":0.2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-10","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-fast/"},{"id":"deepseek/deepseek-v3.2-fast","name":"DeepSeek-V3.2-fast","lab":"deepseek","kind":"text","status":"deprecated","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.4,"output":2,"cacheRead":0.04,"official":false},"cheapest":{"provider":"nebius","input":0.4,"output":2,"cacheRead":0.04},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-27","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-fast/"},{"id":"alibaba/qwen3.5-397b-a17b-fast","name":"Qwen3.5-397B-A17B-fast","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.6,"output":3.6,"cacheRead":0.06,"official":false},"cheapest":{"provider":"nebius","input":0.6,"output":3.6,"cacheRead":0.06},"blendedRef":1.35,"blendedMin":1.35,"blendedTrusted":1.35,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-15","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-a17b-fast/"},{"id":"alibaba/qwen3-next-80b-a3b-thinking-fast","name":"Qwen3-Next-80B-A3B-Thinking-fast","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.15,"output":1.2,"cacheRead":0.015,"official":false},"cheapest":{"provider":"nebius","input":0.15,"output":1.2,"cacheRead":0.015},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":0.4125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-thinking-fast/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507-fast","name":"Qwen3-235B-A22B-Thinking-2507-fast","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.5,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"nebius","input":0.5,"output":2,"cacheRead":0.05},"blendedRef":0.875,"blendedMin":0.875,"blendedTrusted":0.875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507-fast/"},{"id":"primeintellect/intellect-3","name":"INTELLECT-3","lab":"primeintellect","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nebius","input":0.2,"output":1.1,"cacheRead":0.02,"official":false},"cheapest":{"provider":"nebius","input":0.2,"output":1.1,"cacheRead":0.02},"blendedRef":0.425,"blendedMin":0.425,"blendedTrusted":0.425,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":15.7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-01-25","lastUpdated":"2026-02-04","url":"https://llmpricing.dev/m/primeintellect/intellect-3/"},{"id":"misc/echo","name":"Echo","lab":"misc","kind":"text","status":"beta","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"echo","input":10,"output":50,"cacheRead":null,"official":false},"cheapest":{"provider":"echo","input":10,"output":50,"cacheRead":null},"blendedRef":20,"blendedMin":20,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-19","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/misc/echo/"},{"id":"speakleash/bielik-11b-v3.0-instruct","name":"Bielik 11B v3.0 Instruct","lab":"speakleash","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudferro-sherlock","input":0.67,"output":0.67,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudferro-sherlock","input":0.67,"output":0.67,"cacheRead":null},"blendedRef":0.67,"blendedMin":0.67,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/speakleash/bielik-11b-v3.0-instruct/"},{"id":"speakleash/bielik-11b-v2.6-instruct","name":"Bielik 11B v2.6 Instruct","lab":"speakleash","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"cloudferro-sherlock","input":0.67,"output":0.67,"cacheRead":null,"official":false},"cheapest":{"provider":"cloudferro-sherlock","input":0.67,"output":0.67,"cacheRead":null},"blendedRef":0.67,"blendedMin":0.67,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/speakleash/bielik-11b-v2.6-instruct/"},{"id":"openai/gpt-oss-120b-11","name":"OpenAI GPT OSS 120B","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":131000,"contextRange":[128000,131072],"outputLimit":131000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"cloudferro-sherlock","input":2.92,"output":2.92,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.04,"output":0.16,"cacheRead":null},"blendedRef":2.92,"blendedMin":0.07,"blendedTrusted":0.1375,"spread":73,"hostCount":6,"pricedHostCount":6,"aa":null,"usage":null,"releaseDate":"2025-08-28","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-11/"},{"id":"alibaba/qwen3-reranker-0.6b","name":"Qwen3 Reranker 0.6B","lab":"alibaba","kind":"rerank","status":"ga","openWeights":true,"context":40960,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nearai","input":0.01,"output":0.01,"cacheRead":null,"official":false},"cheapest":{"provider":"nearai","input":0.01,"output":0.01,"cacheRead":null},"blendedRef":0.01,"blendedMin":0.01,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-03","lastUpdated":"2025-06-03","url":"https://llmpricing.dev/m/alibaba/qwen3-reranker-0.6b/"},{"id":"openai/qwen3-embedding-0.6b","name":"Qwen3 Embedding 0.6B","lab":"openai","kind":"embedding","status":"beta","openWeights":true,"context":8000,"contextRange":[8000,40960],"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.04,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"nearai","input":0.01,"output":0,"cacheRead":null},"blendedRef":0.03,"blendedMin":0.0075,"blendedTrusted":0.03,"spread":4,"hostCount":3,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-06-03","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/openai/qwen3-embedding-0.6b/"},{"id":"zhipuai/glm-5.1-fp8","name":"GLM-5.1 FP8","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":202752,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"nearai","input":0.85,"output":3.3,"cacheRead":null,"official":false},"cheapest":{"provider":"nearai","input":0.85,"output":3.3,"cacheRead":null},"blendedRef":1.4625,"blendedMin":1.4625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-27","lastUpdated":"2026-03-27","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-fp8/"},{"id":"misc/nomic-embed-text","name":"Nomic Embed Text v1.5","lab":"misc","kind":"embedding","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tinfoil","input":0.05,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"tinfoil","input":0.05,"output":0,"cacheRead":null},"blendedRef":0.0375,"blendedMin":0.0375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-02","lastUpdated":"2024-02","url":"https://llmpricing.dev/m/misc/nomic-embed-text/"},{"id":"zhipuai/glm-5.2-highspeed","name":"GLM-5.2 Highspeed","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zhipuai-coding-plan","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-highspeed/"},{"id":"misc/medgemma-4b","name":"MedGemma 4B","lab":"misc","kind":"text","status":"deprecated","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmtr","input":3,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmtr","input":3,"output":5,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-26","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/misc/medgemma-4b/"},{"id":"trendyol/asure-12b","name":"Trendyol Asure 12B","lab":"trendyol","kind":"text","status":"ga","openWeights":true,"context":40960,"contextRange":null,"outputLimit":40960,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmtr","input":0.1,"output":0.5,"cacheRead":0.025,"official":false},"cheapest":{"provider":"llmtr","input":0.1,"output":0.5,"cacheRead":0.025},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-20","url":"https://llmpricing.dev/m/trendyol/asure-12b/"},{"id":"meta/muse-glimmer-30b-tr","name":"Muse Glimmer 30B (TR)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmtr","input":2,"output":5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"llmtr","input":2,"output":5,"cacheRead":0.5},"blendedRef":2.75,"blendedMin":2.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-10","lastUpdated":"2026-08-10","url":"https://llmpricing.dev/m/meta/muse-glimmer-30b-tr/"},{"id":"misc/magibu-11b-v8","name":"Magibu 11B v8","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmtr","input":0.1,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"llmtr","input":0.1,"output":0.5,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-05","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/misc/magibu-11b-v8/"},{"id":"mistral/voxtral-small-latest","name":"Voxtral Small (latest)","lab":"mistral","kind":"audio","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","audio"],"reference":{"provider":"mistral","input":0.1,"output":0.3,"cacheRead":null,"official":true},"cheapest":{"provider":"llmtr","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-15","lastUpdated":"2025-07-15","url":"https://llmpricing.dev/m/mistral/voxtral-small-latest/"},{"id":"publicai/apertus-8b-instruct","name":"Apertus 8B Instruct","lab":"publicai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmtr","input":0.1,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"llmtr","input":0.1,"output":0.2,"cacheRead":null},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-02","lastUpdated":"2025-09-02","url":"https://llmpricing.dev/m/publicai/apertus-8b-instruct/"},{"id":"publicai/apertus-70b-instruct","name":"Apertus 70B Instruct","lab":"publicai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmtr","input":0.82,"output":2.92,"cacheRead":null,"official":false},"cheapest":{"provider":"llmtr","input":0.82,"output":2.92,"cacheRead":null},"blendedRef":1.345,"blendedMin":1.345,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-02","lastUpdated":"2025-09-02","url":"https://llmpricing.dev/m/publicai/apertus-70b-instruct/"},{"id":"upstage/solar-pro2","name":"Solar Pro 2","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"upstage","input":0.25,"output":0.25,"cacheRead":null,"official":true},"cheapest":{"provider":"upstage","input":0.25,"output":0.25,"cacheRead":null},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":1.7,"hostCount":2,"pricedHostCount":2,"aa":{"idx":12.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/upstage/solar-pro2/"},{"id":"nvidia/nemotron-nano-9b-v2","name":"Nemotron Nano 9B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":0.06,"output":0.23,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":0.06,"output":0.23,"cacheRead":null},"blendedRef":0.1025,"blendedMin":0.1025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-18","lastUpdated":"2025-08-18","url":"https://llmpricing.dev/m/nvidia/nemotron-nano-9b-v2/"},{"id":"google/gemini-3.1-flash-image-2","name":"Gemini 3.1 Flash Image","lab":"google","kind":"image","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"merge-gateway","input":0.5,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":0.5,"output":3,"cacheRead":null},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-image-2/"},{"id":"meta/llama-3.1-8b-instruct-2","name":"Llama 3.1 8B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.22,"output":0.22,"cacheRead":0.22,"official":false},"cheapest":{"provider":"groq","input":0.05,"output":0.08,"cacheRead":null},"blendedRef":0.22,"blendedMin":0.0575,"blendedTrusted":0.0575,"spread":4.4,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-8b-instruct-2/"},{"id":"cohere/command-r-plus-08-2024-3","name":"Command R+ 08-2024","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":4.375,"blendedMin":0.2625,"blendedTrusted":null,"spread":16.7,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-08-30","lastUpdated":"2024-08-30","url":"https://llmpricing.dev/m/cohere/command-r-plus-08-2024-3/"},{"id":"cohere/command-a-03-2025-2","name":"Command A 03-2025","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/cohere/command-a-03-2025-2/"},{"id":"cohere/command-r7b-12-2024-2","name":"Command R7B 12-2024","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":0.0375,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":0.0375,"output":0.15,"cacheRead":null},"blendedRef":0.0656,"blendedMin":0.0656,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-02","lastUpdated":"2024-12-02","url":"https://llmpricing.dev/m/cohere/command-r7b-12-2024-2/"},{"id":"bytedance/dola-seed-2.0-code-preview","name":"Dola Seed 2.0 Code (preview)","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"merge-gateway","input":0.5,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":0.5,"output":3,"cacheRead":null},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-28","lastUpdated":"2026-03-28","url":"https://llmpricing.dev/m/bytedance/dola-seed-2.0-code-preview/"},{"id":"openai/gpt-5.2-chat-latest-2","name":"GPT-5.2 Chat Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[128000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":1.75,"output":14,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2026-01-01","url":"https://llmpricing.dev/m/openai/gpt-5.2-chat-latest-2/"},{"id":"openai/gpt-5.1-chat-latest-2","name":"GPT-5.1 Chat Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":[128000,400000],"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":1.25,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"merge-gateway","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-14","url":"https://llmpricing.dev/m/openai/gpt-5.1-chat-latest-2/"},{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[32000,262144],"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":0.15,"output":0.6,"cacheRead":null,"official":true},"cheapest":{"provider":"edenai","input":0.06,"output":0.18,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.09,"blendedTrusted":0.15,"spread":2.5,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/mistral/mistral-small-latest/"},{"id":"mistral/devstral-medium-2507","name":"Devstral Medium","lab":"mistral","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.4,"output":2,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.4,"output":2,"cacheRead":null},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":12.4,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-07-10","lastUpdated":"2025-07-10","url":"https://llmpricing.dev/m/mistral/devstral-medium-2507/"},{"id":"mistral/mistral-large-2411","name":"Mistral Large 2.1","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":2,"output":6,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":2,"output":6,"cacheRead":null},"blendedRef":3,"blendedMin":3,"blendedTrusted":3,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-11-18","lastUpdated":"2024-11-18","url":"https://llmpricing.dev/m/mistral/mistral-large-2411/"},{"id":"mistral/devstral-small-2507","name":"Devstral Small","lab":"mistral","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.1,"output":0.3,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":11.8,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-07-10","lastUpdated":"2025-07-10","url":"https://llmpricing.dev/m/mistral/devstral-small-2507/"},{"id":"mistral/pixtral-large-latest","name":"Pixtral Large (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":2,"output":6,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":2,"output":6,"cacheRead":null},"blendedRef":3,"blendedMin":3,"blendedTrusted":3,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2024-11-04","url":"https://llmpricing.dev/m/mistral/pixtral-large-latest/"},{"id":"mistral/devstral-medium-latest","name":"Devstral 2 (latest)","lab":"mistral","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.4,"output":2,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.4,"output":2,"cacheRead":null},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/devstral-medium-latest/"},{"id":"mistral/codestral-latest","name":"Codestral (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.3,"output":0.9,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":0.3,"output":0.9,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":0.45,"spread":3.3,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2024-05-29","lastUpdated":"2025-01-04","url":"https://llmpricing.dev/m/mistral/codestral-latest/"},{"id":"mistral/magistral-medium-latest","name":"Magistral Medium (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,262144],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":2,"output":5,"cacheRead":null,"official":true},"cheapest":{"provider":"merge-gateway","input":2,"output":5,"cacheRead":null},"blendedRef":2.75,"blendedMin":2.75,"blendedTrusted":2.75,"spread":1,"hostCount":4,"pricedHostCount":4,"aa":{"idx":12.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-03-17","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/mistral/magistral-medium-latest/"},{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[131072,262144],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":1.5,"output":7.5,"cacheRead":null,"official":true},"cheapest":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396},"blendedRef":3,"blendedMin":0.792,"blendedTrusted":3,"spread":3.8,"hostCount":5,"pricedHostCount":5,"aa":null,"usage":null,"releaseDate":"2026-04-29","lastUpdated":"2026-04-29","url":"https://llmpricing.dev/m/mistral/mistral-medium-latest/"},{"id":"meta/meta-llama-3-3-70b-instruct","name":"Meta-Llama-3_3-70B-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":[128000,131072],"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"ovhcloud","input":0.74,"output":0.74,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.13,"output":0.39,"cacheRead":null},"blendedRef":0.74,"blendedMin":0.195,"blendedTrusted":0.74,"spread":5.7,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-01","lastUpdated":"2025-04-01","url":"https://llmpricing.dev/m/meta/meta-llama-3-3-70b-instruct/"},{"id":"meta/llama-4-scout-17b-16e-instruct-fp8","name":"Llama-4-Scout-17B-16E-Instruct-FP8","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-16e-instruct-fp8/"},{"id":"meta/cerebras-llama-4-scout-17b-16e-instruct","name":"Cerebras-Llama-4-Scout-17B-16E-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/cerebras-llama-4-scout-17b-16e-instruct/"},{"id":"meta/llama-3.3-8b-instruct","name":"Llama-3.3-8B-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-8b-instruct/"},{"id":"meta/cerebras-llama-4-maverick-17b-128e-instruct","name":"Cerebras-Llama-4-Maverick-17B-128E-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/cerebras-llama-4-maverick-17b-128e-instruct/"},{"id":"meta/llama-4-maverick-17b-128e-instruct-fp8-2","name":"Llama 4 Maverick 17B 128E Instruct FP8","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,1000000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"azure-cognitive-services","input":0.25,"output":1,"cacheRead":null},"blendedRef":0,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":1.5,"hostCount":5,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-128e-instruct-fp8-2/"},{"id":"meta/groq-llama-4-maverick-17b-128e-instruct","name":"Groq-Llama-4-Maverick-17B-128E-Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"llama","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/groq-llama-4-maverick-17b-128e-instruct/"},{"id":"openai/openai-gpt-5.2-pro","name":"OpenAI GPT-5.2 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":21,"output":168,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":21,"output":168,"cacheRead":null},"blendedRef":57.75,"blendedMin":57.75,"blendedTrusted":57.75,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/openai-gpt-5.2-pro/"},{"id":"openai/openai-gpt-5.6-luna","name":"OpenAI GPT-5.6 Luna","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.2,"output":1.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"digitalocean","input":0.2,"output":1.2,"cacheRead":0.02},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":0.45,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/openai-gpt-5.6-luna/"},{"id":"openai/gte-large-en-v1.5","name":"GTE Large (v1.5)","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.09,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.09,"output":0,"cacheRead":null},"blendedRef":0.0675,"blendedMin":0.0675,"blendedTrusted":0.0675,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-03-27","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/openai/gte-large-en-v1.5/"},{"id":"anthropic/anthropic-claude-4.6-sonnet","name":"Anthropic Claude Sonnet 4.6","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"digitalocean","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.6-sonnet/"},{"id":"anthropic/anthropic-claude-opus-5","name":"Anthropic Claude Opus 5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-opus-5/"},{"id":"nvidia/nvidia-nemotron-3-super-120b","name":"NVIDIA Nemotron 3 Super 120B  (Public Preview)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.165,"output":0.3575,"cacheRead":0.06,"official":false},"cheapest":{"provider":"digitalocean","input":0.165,"output":0.3575,"cacheRead":0.06},"blendedRef":0.2131,"blendedMin":0.2131,"blendedTrusted":0.2131,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-3-super-120b/"},{"id":"openai/openai-gpt-5.6-terra","name":"OpenAI GPT-5.6 Terra","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"digitalocean","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":4.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/openai-gpt-5.6-terra/"},{"id":"misc/arcee-trinity-large-thinking","name":"Arcee Trinity Large Thinking (Public Preview)","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.25,"output":0.9,"cacheRead":0.06,"official":false},"cheapest":{"provider":"digitalocean","input":0.25,"output":0.9,"cacheRead":0.06},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":0.4125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/misc/arcee-trinity-large-thinking/"},{"id":"anthropic/anthropic-claude-opus-4.5","name":"Anthropic Claude Opus 4.5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-11-24","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-opus-4.5/"},{"id":"openai/openai-gpt-5.4-pro","name":"OpenAI GPT-5.4 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":30,"output":180,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":30,"output":180,"cacheRead":null},"blendedRef":67.5,"blendedMin":67.5,"blendedTrusted":67.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/openai-gpt-5.4-pro/"},{"id":"deepseek/deepseek-3.2","name":"Deepseek 3.2","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":163840,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.25,"output":0.8,"cacheRead":0.075,"official":false},"cheapest":{"provider":"digitalocean","input":0.25,"output":0.8,"cacheRead":0.075},"blendedRef":0.3875,"blendedMin":0.3875,"blendedTrusted":0.3875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/deepseek/deepseek-3.2/"},{"id":"anthropic/anthropic-claude-opus-4.8","name":"Anthropic Claude Opus 4.8","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-opus-4.8/"},{"id":"misc/wan2-2-t2v-a14b","name":"Wan2.2-T2V-A14B","lab":"misc","kind":"video","status":"ga","openWeights":true,"context":100,"contextRange":null,"outputLimit":1,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.6,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.6,"output":0,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":0.45,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/misc/wan2-2-t2v-a14b/"},{"id":"openai/openai-gpt-image-2","name":"OpenAI GPT Image 2","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":8,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":8,"output":30,"cacheRead":null},"blendedRef":13.5,"blendedMin":13.5,"blendedTrusted":13.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-24","lastUpdated":"2025-04-24","url":"https://llmpricing.dev/m/openai/openai-gpt-image-2/"},{"id":"openai/openai-gpt-4.1","name":"OpenAI GPT-4.1","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":2,"output":8,"cacheRead":0.5},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/openai-gpt-4.1/"},{"id":"openai/openai-gpt-4o","name":"OpenAI GPT-4o","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":2.5,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"digitalocean","input":2.5,"output":10,"cacheRead":1.25},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-05-13","lastUpdated":"2024-08-06","url":"https://llmpricing.dev/m/openai/openai-gpt-4o/"},{"id":"nvidia/nemotron-3-ultra-550b-3","name":"Nemotron 3 Ultra","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[131072,1000000],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.75,"output":2.75,"cacheRead":0.15,"official":false},"cheapest":{"provider":"vercel","input":0.6,"output":2.4,"cacheRead":0.12},"blendedRef":1.25,"blendedMin":1.05,"blendedTrusted":1.05,"spread":1.5,"hostCount":4,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-3/"},{"id":"mistral/mistral-nemo-instruct-2407-2","name":"Mistral Nemo Instruct","lab":"mistral","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.3,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.3,"output":0.3,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":0.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/mistral/mistral-nemo-instruct-2407-2/"},{"id":"openai/openai-gpt-5.5","name":"OpenAI GPT-5.5","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":11.25,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/openai/openai-gpt-5.5/"},{"id":"anthropic/anthropic-claude-4.5-sonnet","name":"Anthropic Claude 4.5 Sonnet","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"digitalocean","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.5-sonnet/"},{"id":"misc/stable-diffusion-3.5-large","name":"Stable Diffusion 3.5 Large","lab":"misc","kind":"image","status":"ga","openWeights":true,"context":256,"contextRange":null,"outputLimit":1,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.08,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.08,"output":0,"cacheRead":null},"blendedRef":0.06,"blendedMin":0.06,"blendedTrusted":0.06,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/misc/stable-diffusion-3.5-large/"},{"id":"openai/all-mini-lm-l6-v2","name":"All-MiniLM-L6-v2","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":256,"contextRange":null,"outputLimit":384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.009,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.009,"output":0,"cacheRead":null},"blendedRef":0.0067,"blendedMin":0.0067,"blendedTrusted":0.0067,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2021-08-30","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/openai/all-mini-lm-l6-v2/"},{"id":"openai/openai-gpt-5.4","name":"OpenAI GPT-5.4","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"digitalocean","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":5.625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/openai-gpt-5.4/"},{"id":"anthropic/anthropic-claude-opus-4.7","name":"Anthropic Claude Opus 4.7","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-opus-4.7/"},{"id":"openai/openai-gpt-5.4-mini","name":"OpenAI GPT-5.4 Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.75,"output":4.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"digitalocean","input":0.75,"output":4.5,"cacheRead":0.075},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":1.6875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/openai-gpt-5.4-mini/"},{"id":"anthropic/anthropic-claude-4.1-opus","name":"Anthropic Claude 4.1 Opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"digitalocean","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":30,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.1-opus/"},{"id":"meta/llama3.3-70b-instruct","name":"Llama 3.3 Instruct (70B)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.65,"output":0.65,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.65,"output":0.65,"cacheRead":null},"blendedRef":0.65,"blendedMin":0.65,"blendedTrusted":0.65,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":9.3,"coding":11.9,"agentic":null,"speed":88,"ttft":1.61,"taskCost":null},"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama3.3-70b-instruct/"},{"id":"openai/openai-gpt-5-mini","name":"OpenAI GPT-5 Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.25,"output":2,"cacheRead":0.024999999999999998,"official":false},"cheapest":{"provider":"digitalocean","input":0.25,"output":2,"cacheRead":0.025},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":0.6875,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/openai-gpt-5-mini/"},{"id":"alibaba/qwen3-tts-voicedesign","name":"Qwen3 TTS VoiceDesign","lab":"alibaba","kind":"audio","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":1,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/alibaba/qwen3-tts-voicedesign/"},{"id":"anthropic/anthropic-claude-fable-5","name":"Anthropic Claude Fable 5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"digitalocean","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":20,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-fable-5/"},{"id":"anthropic/anthropic-claude-5-sonnet","name":"Anthropic Claude Sonnet 5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":2,"output":10,"cacheRead":0.2,"official":false},"cheapest":{"provider":"digitalocean","input":2,"output":10,"cacheRead":0.2},"blendedRef":4,"blendedMin":4,"blendedTrusted":4,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-5-sonnet/"},{"id":"openai/openai-gpt-5.3-codex","name":"OpenAI GPT-5.3 Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"digitalocean","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":4.8125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/openai-gpt-5.3-codex/"},{"id":"minimax/minimax-m2.5-5","name":"MiniMax M2.5 (Public Preview)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.225,"output":0.9,"cacheRead":0.06,"official":false},"cheapest":{"provider":"digitalocean","input":0.225,"output":0.9,"cacheRead":0.06},"blendedRef":0.3938,"blendedMin":0.3938,"blendedTrusted":0.3938,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-5/"},{"id":"anthropic/anthropic-claude-opus-4.6","name":"Anthropic Claude Opus 4.6","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-opus-4.6/"},{"id":"anthropic/anthropic-claude-haiku-4.5","name":"Anthropic Claude Haiku 4.5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":1,"output":5,"cacheRead":0.1,"official":false},"cheapest":{"provider":"digitalocean","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-haiku-4.5/"},{"id":"openai/multi-qa-mpnet-base-dot-v1","name":"Multi-QA-mpnet-base-dot-v1","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":512,"contextRange":null,"outputLimit":768,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.009,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.009,"output":0,"cacheRead":null},"blendedRef":0.0067,"blendedMin":0.0067,"blendedTrusted":0.0067,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2021-08-30","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/openai/multi-qa-mpnet-base-dot-v1/"},{"id":"openai/openai-gpt-4o-mini","name":"OpenAI GPT-4o mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.15,"output":0.6,"cacheRead":0.075,"official":false},"cheapest":{"provider":"digitalocean","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/openai-gpt-4o-mini/"},{"id":"meta/llama3-8b-instruct","name":"Llama 3.1 Instruct (8B)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.198,"output":0.198,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.198,"output":0.198,"cacheRead":null},"blendedRef":0.198,"blendedMin":0.198,"blendedTrusted":0.198,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":7.4,"coding":5.4,"agentic":null,"speed":137,"ttft":0.93,"taskCost":null},"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama3-8b-instruct/"},{"id":"anthropic/anthropic-claude-3-opus","name":"Claude 3 Opus","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"digitalocean","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":30,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":11.8,"coding":19.5,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-02-29","lastUpdated":"2024-02-29","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-3-opus/"},{"id":"openai/openai-gpt-image-1.5","name":"OpenAI GPT Image 1.5","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":10,"cacheRead":1,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":10,"cacheRead":1},"blendedRef":6.25,"blendedMin":6.25,"blendedTrusted":6.25,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-25","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/openai/openai-gpt-image-1.5/"},{"id":"openai/openai-gpt-5-nano","name":"OpenAI GPT-5 Nano","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.05,"output":0.4,"cacheRead":0.005,"official":false},"cheapest":{"provider":"helicone","input":0.049999999999999996,"output":0.39999999999999997,"cacheRead":0.005},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":0.1375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/openai-gpt-5-nano/"},{"id":"misc/bge-reranker-v2-m3","name":"BGE Reranker v2 M3","lab":"misc","kind":"embedding","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":1,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.01,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.01,"output":0,"cacheRead":null},"blendedRef":0.0075,"blendedMin":0.0075,"blendedTrusted":0.0075,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-03-12","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/misc/bge-reranker-v2-m3/"},{"id":"openai/openai-gpt-5.4-nano","name":"OpenAI GPT-5.4 Nano","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.2,"output":1.25,"cacheRead":0.02,"official":false},"cheapest":{"provider":"digitalocean","input":0.2,"output":1.25,"cacheRead":0.02},"blendedRef":0.4625,"blendedMin":0.4625,"blendedTrusted":0.4625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/openai-gpt-5.4-nano/"},{"id":"openai/e5-large-v2","name":"E5 Large v2","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":512,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"digitalocean","input":0.02,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"digitalocean","input":0.02,"output":0,"cacheRead":null},"blendedRef":0.015,"blendedMin":0.015,"blendedTrusted":0.015,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-05-19","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/openai/e5-large-v2/"},{"id":"openai/openai-gpt-5.6-sol","name":"OpenAI GPT-5.6 Sol","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"digitalocean","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":11.25,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/openai-gpt-5.6-sol/"},{"id":"openai/gpt-oss-20b-5","name":"OpenAI GPT-oss-20b","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"digitalocean","input":0.05,"output":0.45,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.04,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.0675,"blendedTrusted":0.075,"spread":1.3,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/openai/gpt-oss-20b-5/"},{"id":"fal-ai/fast-sdxl","name":"Fast SDXL","lab":"fal-ai","kind":"image","status":"ga","openWeights":true,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-07-26","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/fal-ai/fast-sdxl/"},{"id":"fal-ai/multilingual-v2","name":"ElevenLabs Multilingual TTS v2","lab":"fal-ai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-08-22","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/fal-ai/multilingual-v2/"},{"id":"fal-ai/text-to-audio","name":"Stable Audio 2.5 (Text-to-Audio)","lab":"fal-ai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-08","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/fal-ai/text-to-audio/"},{"id":"google/imagen-4.0-fast","name":"Imagen 4 Fast","lab":"google","kind":"image","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-06-25","url":"https://llmpricing.dev/m/google/imagen-4.0-fast/"},{"id":"google/imagen-4.0-ultra","name":"Imagen 4 Ultra","lab":"google","kind":"image","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-24","url":"https://llmpricing.dev/m/google/imagen-4.0-ultra/"},{"id":"leonardo-ai/lucid-realism","name":"Lucid Realism","lab":"leonardo-ai","kind":"image","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-01","lastUpdated":"2025-06-01","url":"https://llmpricing.dev/m/leonardo-ai/lucid-realism/"},{"id":"leonardo-ai/lucid-origin","name":"Lucid Origin","lab":"leonardo-ai","kind":"image","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-01","lastUpdated":"2025-06-01","url":"https://llmpricing.dev/m/leonardo-ai/lucid-origin/"},{"id":"xai/grok-4-2","name":"Grok 4","lab":"xai","kind":"text","status":"deprecated","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"abacus","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"fastrouter","input":3,"output":15,"cacheRead":0.75},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":1,"hostCount":5,"pricedHostCount":5,"aa":{"idx":34.1,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-07-09","lastUpdated":"2025-07-10","url":"https://llmpricing.dev/m/xai/grok-4-2/"},{"id":"bytedance/seedance-2","name":"Seedance 2","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-04-01","url":"https://llmpricing.dev/m/bytedance/seedance-2/"},{"id":"openai/gpt-realtime-1.5","name":"GPT Realtime 1.5","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","audio","image"],"reference":{"provider":"vercel","input":4,"output":16,"cacheRead":0.4,"official":false},"cheapest":{"provider":"fastrouter","input":4,"output":16,"cacheRead":null},"blendedRef":7,"blendedMin":7,"blendedTrusted":7,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-06-01","lastUpdated":"2026-02-23","url":"https://llmpricing.dev/m/openai/gpt-realtime-1.5/"},{"id":"alibaba/qwen3-coder-3","name":"Qwen3 Coder","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0.45,"output":1.8,"cacheRead":null,"official":false},"cheapest":{"provider":"fastrouter","input":0.3,"output":1.2,"cacheRead":null},"blendedRef":0.7875,"blendedMin":0.525,"blendedTrusted":null,"spread":1.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-3/"},{"id":"wanx/wan-v2-6","name":"Wan 2.6","lab":"wanx","kind":"video","status":"ga","openWeights":true,"context":400000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/wanx/wan-v2-6/"},{"id":"mistral/voxtral-mini-3b","name":"Voxtral Mini 3B","lab":"mistral","kind":"audio","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["audio"],"reference":{"provider":"privatemode-ai","input":0.00462,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"privatemode-ai","input":0.00462,"output":0,"cacheRead":null},"blendedRef":0.0035,"blendedMin":0.0035,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07","lastUpdated":"2025-07","url":"https://llmpricing.dev/m/mistral/voxtral-mini-3b/"},{"id":"misc/zdev","name":"ZDev","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"zeldoc","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-15","lastUpdated":"2026-04-15","url":"https://llmpricing.dev/m/misc/zdev/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507-4","name":"Qwen 3 235B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"io-net","input":0.11,"output":0.6,"cacheRead":0.055,"official":false},"cheapest":{"provider":"io-net","input":0.11,"output":0.6,"cacheRead":0.055},"blendedRef":0.2325,"blendedMin":0.2325,"blendedTrusted":0.2325,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-01","lastUpdated":"2025-07-01","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507-4/"},{"id":"alibaba/qwen3-next-80b-a3b-instruct-4","name":"Qwen 3 Next 80B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"io-net","input":0.1,"output":0.8,"cacheRead":0.05,"official":false},"cheapest":{"provider":"io-net","input":0.1,"output":0.8,"cacheRead":0.05},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":0.275,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-10","lastUpdated":"2025-01-10","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b-a3b-instruct-4/"},{"id":"mistral/mistral-large-instruct-2411","name":"Mistral Large Instruct 2411","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"io-net","input":2,"output":6,"cacheRead":1,"official":false},"cheapest":{"provider":"io-net","input":2,"output":6,"cacheRead":1},"blendedRef":3,"blendedMin":3,"blendedTrusted":3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2024-11-01","url":"https://llmpricing.dev/m/mistral/mistral-large-instruct-2411/"},{"id":"mistral/devstral-small-2505-2","name":"Devstral Small 2505","lab":"mistral","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.1,"output":0.3,"cacheRead":null,"official":true},"cheapest":{"provider":"io-net","input":0.05,"output":0.22,"cacheRead":0.025},"blendedRef":0.15,"blendedMin":0.0925,"blendedTrusted":0.0925,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-01","lastUpdated":"2025-05-07","url":"https://llmpricing.dev/m/mistral/devstral-small-2505-2/"},{"id":"google/gemma-4-31b-it-9","name":"Gemma 4 31B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[128000,262144],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["audio","image","text","video"],"reference":{"provider":"togetherai","input":0.39,"output":0.97,"cacheRead":null,"official":false},"cheapest":{"provider":"berget","input":0.275,"output":0.55,"cacheRead":null},"blendedRef":0.535,"blendedMin":0.3438,"blendedTrusted":0.535,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-9/"},{"id":"mistral/mistral-medium-3.5-128b","name":"Mistral Medium 3.5 128B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":[256000,262144],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"scaleway","input":1.5,"output":7.5,"cacheRead":null,"official":false},"cheapest":{"provider":"berget","input":1.65,"output":5.5,"cacheRead":null},"blendedRef":3,"blendedMin":2.6125,"blendedTrusted":3,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-04-29","lastUpdated":"2026-04-29","url":"https://llmpricing.dev/m/mistral/mistral-medium-3.5-128b/"},{"id":"xiaomi/mimo-v2.5-pro-ultraspeed","name":"MiMo-V2.5-Pro-UltraSpeed","lab":"xiaomi","kind":"text","status":"beta","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"xiaomi","input":1.305,"output":2.61,"cacheRead":0.0108,"official":true},"cheapest":{"provider":"xiaomi","input":1.305,"output":2.61,"cacheRead":0.0108},"blendedRef":1.6313,"blendedMin":1.6313,"blendedTrusted":1.6313,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-08","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-pro-ultraspeed/"},{"id":"alibaba/qwen3-livetranslate-flash-realtime","name":"Qwen3-LiveTranslate Flash Realtime","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":53248,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"alibaba","input":10,"output":10,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba","input":10,"output":10,"cacheRead":null},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-22","lastUpdated":"2025-09-22","url":"https://llmpricing.dev/m/alibaba/qwen3-livetranslate-flash-realtime/"},{"id":"alibaba/qwen-plus-character-ja","name":"Qwen Plus Character (Japanese)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":512,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"alibaba","input":0.5,"output":1.4,"cacheRead":null,"official":true},"cheapest":{"provider":"alibaba","input":0.5,"output":1.4,"cacheRead":null},"blendedRef":0.725,"blendedMin":0.725,"blendedTrusted":0.725,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01","lastUpdated":"2024-01","url":"https://llmpricing.dev/m/alibaba/qwen-plus-character-ja/"},{"id":"sakana/fugu","name":"Fugu","lab":"sakana","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":1000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-15","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/sakana/fugu/"},{"id":"zhipuai/glm-4.6v-flash-2","name":"GLM 4.6V FlashX","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,200000],"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"llmgateway","input":0.04,"output":0.4,"cacheRead":0.004,"official":false},"cheapest":{"provider":"zenmux","input":0.02,"output":0.21,"cacheRead":0.0043},"blendedRef":0.13,"blendedMin":0.0675,"blendedTrusted":null,"spread":2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-flash-2/"},{"id":"zhipuai/glm-4.6v-flash-free","name":"GLM 4.6V Flash (Free)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/zhipuai/glm-4.6v-flash-free/"},{"id":"deepseek/deepseek-chat-3","name":"DeepSeek-V3.2 (Non-thinking Mode)","lab":"deepseek","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zenmux","input":0.28,"output":0.42,"cacheRead":0.03,"official":false},"cheapest":{"provider":"zenmux","input":0.28,"output":0.42,"cacheRead":0.03},"blendedRef":0.315,"blendedMin":0.315,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-chat-3/"},{"id":"xai/grok-4.2-fast-non-reasoning","name":"Grok 4.2 Fast Non Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":3,"output":9,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":3,"output":9,"cacheRead":null},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-20","lastUpdated":"2026-03-20","url":"https://llmpricing.dev/m/xai/grok-4.2-fast-non-reasoning/"},{"id":"xai/grok-4.2-fast","name":"Grok 4.2 Fast","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":3,"output":9,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":3,"output":9,"cacheRead":null},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-20","lastUpdated":"2026-03-20","url":"https://llmpricing.dev/m/xai/grok-4.2-fast/"},{"id":"xai/grok-4-fast-2","name":"Grok 4 Fast","lab":"xai","kind":"text","status":"deprecated","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"zenmux","input":0.2,"output":0.5,"cacheRead":0.05,"official":false},"cheapest":{"provider":"zenmux","input":0.2,"output":0.5,"cacheRead":0.05},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":27.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-09-19","lastUpdated":"2025-09-19","url":"https://llmpricing.dev/m/xai/grok-4-fast-2/"},{"id":"xai/grok-4.1-fast-2","name":"Grok 4.1 Fast","lab":"xai","kind":"text","status":"deprecated","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"ofox","input":0.2,"output":0.5,"cacheRead":0.05,"official":false},"cheapest":{"provider":"zenmux","input":0.2,"output":0.5,"cacheRead":0.05},"blendedRef":0.275,"blendedMin":0.275,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":31.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-19","lastUpdated":"2025-11-19","url":"https://llmpricing.dev/m/xai/grok-4.1-fast-2/"},{"id":"moonshotai/kimi-k3-free","name":"Kimi K3 (Free)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-free/"},{"id":"anthropic/claude-sonnet-5-free","name":"Claude Sonnet 5 (Free)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"zenmux","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-5-free/"},{"id":"openai/gpt-5.3-chat","name":"GPT-5.3 Chat","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16380,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"zenmux","input":1.75,"output":14,"cacheRead":null,"official":false},"cheapest":{"provider":"requesty","input":1.575,"output":12.6,"cacheRead":0.1575},"blendedRef":4.8125,"blendedMin":4.3313,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-20","lastUpdated":"2026-03-20","url":"https://llmpricing.dev/m/openai/gpt-5.3-chat/"},{"id":"openai/gpt-5.5-instant","name":"GPT-5.5 Instant","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"zenmux","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"zenmux","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":34.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-05-05","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/openai/gpt-5.5-instant/"},{"id":"stepfun/step-3","name":"Step-3","lab":"stepfun","kind":"text","status":"deprecated","openWeights":false,"context":65536,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"zenmux","input":0.21,"output":0.57,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.21,"output":0.57,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-31","lastUpdated":"2025-07-31","url":"https://llmpricing.dev/m/stepfun/step-3/"},{"id":"stepfun/step-3.7-flash-free","name":"Step 3.7 Flash (Free)","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/stepfun/step-3.7-flash-free/"},{"id":"sapiens-ai/agnes-1.5-pro","name":"Agnes 1.5 Pro","lab":"sapiens-ai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"zenmux","input":0.16,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.16,"output":0.8,"cacheRead":null},"blendedRef":0.32,"blendedMin":0.32,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-21","lastUpdated":"2026-03-21","url":"https://llmpricing.dev/m/sapiens-ai/agnes-1.5-pro/"},{"id":"sapiens-ai/agnes-1.5-lite","name":"Agnes 1.5 Lite","lab":"sapiens-ai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"zenmux","input":0.12,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.12,"output":0.6,"cacheRead":null},"blendedRef":0.24,"blendedMin":0.24,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-26","lastUpdated":"2026-03-26","url":"https://llmpricing.dev/m/sapiens-ai/agnes-1.5-lite/"},{"id":"volcengine/doubao-seed-code","name":"Doubao-Seed-Code","lab":"volcengine","kind":"text","status":"deprecated","openWeights":false,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"zenmux","input":0.17,"output":1.12,"cacheRead":0.03,"official":false},"cheapest":{"provider":"zenmux","input":0.17,"output":1.12,"cacheRead":0.03},"blendedRef":0.4075,"blendedMin":0.4075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":26.5,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-11","lastUpdated":"2025-11-11","url":"https://llmpricing.dev/m/volcengine/doubao-seed-code/"},{"id":"volcengine/doubao-seed-1.8","name":"Doubao-Seed-1.8","lab":"volcengine","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":0.11,"output":0.28,"cacheRead":0.02,"official":false},"cheapest":{"provider":"zenmux","input":0.11,"output":0.28,"cacheRead":0.02},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/volcengine/doubao-seed-1.8/"},{"id":"inclusionai/ling-1t","name":"Ling-1T","lab":"inclusionai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"bailing","input":0.57,"output":2.29,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.56,"output":2.24,"cacheRead":0.11},"blendedRef":1,"blendedMin":0.98,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":12.7,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-10-09","lastUpdated":"2025-10-09","url":"https://llmpricing.dev/m/inclusionai/ling-1t/"},{"id":"inclusionai/ring-1t","name":"Ring-1T","lab":"inclusionai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"bailing","input":0.57,"output":2.29,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.56,"output":2.24,"cacheRead":0.11},"blendedRef":1,"blendedMin":0.98,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":16.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-10-12","lastUpdated":"2025-10-12","url":"https://llmpricing.dev/m/inclusionai/ring-1t/"},{"id":"inclusionai/ring-2.6-1t-2","name":"inclusionAI: Ring-2.6-1T","lab":"inclusionai","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":65000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"zenmux","input":0.3,"output":2.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"zenmux","input":0.3,"output":2.5,"cacheRead":0.06},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-14","url":"https://llmpricing.dev/m/inclusionai/ring-2.6-1t-2/"},{"id":"baidu/ernie-5.0-thinking-preview-2","name":"ERNIE 5.0","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"zenmux","input":0.84,"output":3.37,"cacheRead":null,"official":false},"cheapest":{"provider":"zenmux","input":0.84,"output":3.37,"cacheRead":null},"blendedRef":1.4725,"blendedMin":1.4725,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-22","lastUpdated":"2026-01-22","url":"https://llmpricing.dev/m/baidu/ernie-5.0-thinking-preview-2/"},{"id":"alibaba/qwen3.5-397b","name":"qwen3.5:397b","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"venice","input":0.75,"output":4.5,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":0.75,"output":4.5,"cacheRead":null},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-15","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b/"},{"id":"nvidia/nemotron-3-nano-30b-2","name":"nemotron-3-nano:30b","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":[262144,1048576],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.06,"output":0.24,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.06,"output":0.24,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-15","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-30b-2/"},{"id":"perplexity/sonar-deep-research-3","name":"Perplexity Sonar Deep Research","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[127000,128000],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"perplexity","input":2,"output":8,"cacheRead":null,"official":true},"cheapest":{"provider":"perplexity","input":2,"output":8,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-02-01","lastUpdated":"2025-09-01","url":"https://llmpricing.dev/m/perplexity/sonar-deep-research-3/"},{"id":"amazon/amazon-nova-pro","name":"amazon--nova-pro","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"sap-ai-core","input":0.56,"output":2.13,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.56,"output":2.13,"cacheRead":null},"blendedRef":0.9525,"blendedMin":0.9525,"blendedTrusted":0.9525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-03","url":"https://llmpricing.dev/m/amazon/amazon-nova-pro/"},{"id":"anthropic/anthropic-claude-3-sonnet","name":"anthropic--claude-3-sonnet","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-03-04","lastUpdated":"2024-03-04","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-3-sonnet/"},{"id":"misc/nvidia-llama-3.2-nv-embedqa-1b","name":"nvidia--llama-3.2-nv-embedqa-1b","lab":"misc","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"sap-ai-core","input":0.07,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.07,"output":0,"cacheRead":null},"blendedRef":0.0525,"blendedMin":0.0525,"blendedTrusted":0.0525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/misc/nvidia-llama-3.2-nv-embedqa-1b/"},{"id":"anthropic/anthropic-claude-4.8-opus","name":"anthropic--claude-4.8-opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.8-opus/"},{"id":"misc/amazon-titan-embed-text","name":"amazon--titan-embed-text","lab":"misc","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"sap-ai-core","input":0.14,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.14,"output":0,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":0.105,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-30","lastUpdated":"2024-04-30","url":"https://llmpricing.dev/m/misc/amazon-titan-embed-text/"},{"id":"anthropic/anthropic-claude-4-opus","name":"anthropic--claude-4-opus","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"sap-ai-core","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":30,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4-opus/"},{"id":"mistral/mistralai-mistral-medium-instruct","name":"mistralai--mistral-medium-instruct","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"sap-ai-core","input":0.36,"output":1.22,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.36,"output":1.22,"cacheRead":null},"blendedRef":0.575,"blendedMin":0.575,"blendedTrusted":0.575,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-07","lastUpdated":"2025-05-07","url":"https://llmpricing.dev/m/mistral/mistralai-mistral-medium-instruct/"},{"id":"anthropic/anthropic-claude-4.6-opus","name":"anthropic--claude-4.6-opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.6-opus/"},{"id":"mistral/mistralai-mistral-small","name":"mistralai--mistral-small","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"sap-ai-core","input":0.07,"output":0.28,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.07,"output":0.28,"cacheRead":null},"blendedRef":0.1225,"blendedMin":0.1225,"blendedTrusted":0.1225,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/mistral/mistralai-mistral-small/"},{"id":"amazon/amazon-nova-lite","name":"amazon--nova-lite","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"sap-ai-core","input":0.3,"output":2.37,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.3,"output":2.37,"cacheRead":null},"blendedRef":0.8175,"blendedMin":0.8175,"blendedTrusted":0.8175,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/amazon/amazon-nova-lite/"},{"id":"anthropic/anthropic-claude-4.5-haiku","name":"anthropic--claude-4.5-haiku","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"helicone","input":1,"output":5,"cacheRead":0.09999999999999999,"official":false},"cheapest":{"provider":"sap-ai-core","input":1,"output":5,"cacheRead":0.1},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.5-haiku/"},{"id":"amazon/amazon-nova-micro","name":"amazon--nova-micro","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"sap-ai-core","input":0.03,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.03,"output":0.1,"cacheRead":null},"blendedRef":0.0475,"blendedMin":0.0475,"blendedTrusted":0.0475,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-03","url":"https://llmpricing.dev/m/amazon/amazon-nova-micro/"},{"id":"anthropic/anthropic-claude-4.6-sonnet-2","name":"anthropic--claude-4.6-sonnet","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.6-sonnet-2/"},{"id":"anthropic/anthropic-claude-3-haiku","name":"Anthropic: Claude 3 Haiku","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":0.25,"output":1.25,"cacheRead":0.03,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.25,"output":1.25,"cacheRead":0.03},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":0.5,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-03-13","lastUpdated":"2024-03-13","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-3-haiku/"},{"id":"anthropic/anthropic-claude-4.5-opus","name":"anthropic--claude-4.5-opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-11-24","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.5-opus/"},{"id":"anthropic/anthropic-claude-4.7-opus","name":"anthropic--claude-4.7-opus","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"sap-ai-core","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":10,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4.7-opus/"},{"id":"anthropic/anthropic-claude-3.7-sonnet","name":"anthropic--claude-3.7-sonnet","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004,"official":false},"cheapest":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-02-24","lastUpdated":"2025-02-24","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-3.7-sonnet/"},{"id":"anthropic/anthropic-claude-3-opus-2","name":"anthropic--claude-3-opus","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"sap-ai-core","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":30,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-02-29","lastUpdated":"2024-02-29","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-3-opus-2/"},{"id":"anthropic/anthropic-claude-3.5-sonnet","name":"anthropic--claude-3.5-sonnet","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2024-10-22","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-3.5-sonnet/"},{"id":"anthropic/anthropic-claude-4-sonnet","name":"anthropic--claude-4-sonnet","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"sap-ai-core","input":3,"output":15,"cacheRead":0.3},"blendedRef":6,"blendedMin":6,"blendedTrusted":6,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/anthropic-claude-4-sonnet/"},{"id":"misc/sap-abap-1","name":"sap-abap-1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"sap-ai-core","input":0.48,"output":1.7,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.48,"output":1.7,"cacheRead":null},"blendedRef":0.785,"blendedMin":0.785,"blendedTrusted":0.785,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-26","lastUpdated":"2025-11-26","url":"https://llmpricing.dev/m/misc/sap-abap-1/"},{"id":"cohere/cohere-command-a-reasoning","name":"cohere--command-a-reasoning","lab":"cohere","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"sap-ai-core","input":0.63,"output":5.05,"cacheRead":null,"official":false},"cheapest":{"provider":"sap-ai-core","input":0.63,"output":5.05,"cacheRead":null},"blendedRef":1.735,"blendedMin":1.735,"blendedTrusted":1.735,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/cohere/cohere-command-a-reasoning/"},{"id":"google/gemma-3","name":"Google Gemma 3","lab":"google","kind":"text","status":"ga","openWeights":true,"context":125000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"inference","input":0.15,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"inference","input":0.15,"output":0.3,"cacheRead":null},"blendedRef":0.1875,"blendedMin":0.1875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/google/gemma-3/"},{"id":"osmosis/osmosis-structure-0.6b","name":"Osmosis Structure 0.6B","lab":"osmosis","kind":"text","status":"ga","openWeights":true,"context":4000,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"inference","input":0.1,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"inference","input":0.1,"output":0.5,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/osmosis/osmosis-structure-0.6b/"},{"id":"alibaba/qwen-2.5-7b-vision-instruct","name":"Qwen 2.5 7B Vision Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":125000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"inference","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"inference","input":0.2,"output":0.2,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/alibaba/qwen-2.5-7b-vision-instruct/"},{"id":"mistral/mistral-nemo-12b-instruct","name":"Mistral Nemo 12B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":16000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"inference","input":0.038,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"inference","input":0.038,"output":0.1,"cacheRead":null},"blendedRef":0.0535,"blendedMin":0.0535,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/mistral/mistral-nemo-12b-instruct/"},{"id":"zhipuai/glm-4.5-fp8","name":"GLM 4.5 FP8","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"submodel","input":0.2,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"submodel","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-07-28","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-fp8/"},{"id":"amazon/nova-2-pro-v1","name":"Nova 2 Pro","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video","pdf"],"reference":{"provider":"nova","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2026-01-03","url":"https://llmpricing.dev/m/amazon/nova-2-pro-v1/"},{"id":"liquidai/lfm2-24b-a2b","name":"LFM2-24B-A2B","lab":"liquidai","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.03,"output":0.12,"cacheRead":0.03,"official":false},"cheapest":{"provider":"togetherai","input":0.03,"output":0.12,"cacheRead":null},"blendedRef":0.0525,"blendedMin":0.0525,"blendedTrusted":0.0525,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":4.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-02-25","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/liquidai/lfm2-24b-a2b/"},{"id":"google/gemma-3n-e4b-it-3","name":"Gemma 3N E4B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.06,"output":0.12,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.06,"output":0.12,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":0.075,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":1,"coding":3.2,"agentic":null,"speed":55,"ttft":1.5,"taskCost":null},"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/google/gemma-3n-e4b-it-3/"},{"id":"essentialai/rnj-1-instruct","name":"Rnj-1 Instruct","lab":"essentialai","kind":"text","status":"deprecated","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.15,"output":0.15,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-05","lastUpdated":"2025-12-05","url":"https://llmpricing.dev/m/essentialai/rnj-1-instruct/"},{"id":"alibaba/qwen3-coder-next-fp8","name":"Qwen3 Coder Next FP8","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":[256144,262144],"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.5,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.5,"output":1.2,"cacheRead":null},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":0.675,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-03","lastUpdated":"2026-02-03","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-next-fp8/"},{"id":"alibaba/qwen2.5-7b-instruct-turbo","name":"Qwen 2.5 7B Instruct Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.3,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.3,"output":0.3,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":0.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-19","lastUpdated":"2024-09-19","url":"https://llmpricing.dev/m/alibaba/qwen2.5-7b-instruct-turbo/"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507-tput","name":"Qwen3 235B A22B Instruct 2507 FP8","lab":"alibaba","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.2,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.2,"output":0.6,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":0.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-25","lastUpdated":"2025-07-25","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-instruct-2507-tput/"},{"id":"google/gemma-4-31b-it-10","name":"Pearl AI Gemma 4 31B Instruct","lab":"google","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.28,"output":0.86,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.28,"output":0.86,"cacheRead":null},"blendedRef":0.425,"blendedMin":0.425,"blendedTrusted":0.425,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-10/"},{"id":"meta/meta-llama-3-8b-instruct-lite","name":"Meta Llama 3 8B Instruct Lite","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"togetherai","input":0.14,"output":0.14,"cacheRead":null,"official":false},"cheapest":{"provider":"togetherai","input":0.14,"output":0.14,"cacheRead":null},"blendedRef":0.14,"blendedMin":0.14,"blendedTrusted":0.14,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-18","lastUpdated":"2024-04-18","url":"https://llmpricing.dev/m/meta/meta-llama-3-8b-instruct-lite/"},{"id":"bytedance-seed/seed-1-8","name":"Seed 1.8","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"ofox","input":0.12,"output":0.29,"cacheRead":0.023},"blendedRef":0.6875,"blendedMin":0.1625,"blendedTrusted":0.6875,"spread":2.1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-28","lastUpdated":"2025-12-28","url":"https://llmpricing.dev/m/bytedance-seed/seed-1-8/"},{"id":"bytedance-seed/seed-2.1-pro","name":"Seed 2.1 Pro","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"ofox","input":0.7072,"output":3.536,"cacheRead":0.1416,"official":false},"cheapest":{"provider":"ofox","input":0.7072,"output":3.536,"cacheRead":0.1416},"blendedRef":1.4144,"blendedMin":1.4144,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/bytedance-seed/seed-2.1-pro/"},{"id":"bytedance-seed/seed-evolving","name":"Seed Evolving","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"ofox","input":0.884,"output":4.42,"cacheRead":0.177,"official":false},"cheapest":{"provider":"ofox","input":0.884,"output":4.42,"cacheRead":0.177},"blendedRef":1.768,"blendedMin":1.768,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/bytedance-seed/seed-evolving/"},{"id":"bytedance-seed/seed-character","name":"Seed Character","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"ofox","input":0.177,"output":0.884,"cacheRead":0.024,"official":false},"cheapest":{"provider":"ofox","input":0.177,"output":0.884,"cacheRead":0.024},"blendedRef":0.3538,"blendedMin":0.3538,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/bytedance-seed/seed-character/"},{"id":"bytedance-seed/seed-1-6-vision","name":"Seed 1.6 Vision","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"ofox","input":0.12,"output":1.15,"cacheRead":0.023,"official":false},"cheapest":{"provider":"ofox","input":0.12,"output":1.15,"cacheRead":0.023},"blendedRef":0.3775,"blendedMin":0.3775,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-15","lastUpdated":"2025-08-15","url":"https://llmpricing.dev/m/bytedance-seed/seed-1-6-vision/"},{"id":"minimax/minimax-m2.5-lightning","name":"MiniMax-M2.5 Lightning","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"ofox","input":0.3,"output":2.4,"cacheRead":0.03,"official":false},"cheapest":{"provider":"ofox","input":0.3,"output":2.4,"cacheRead":0.03},"blendedRef":0.825,"blendedMin":0.825,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-13","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-lightning/"},{"id":"minimax/minimax-m2.1-lightning-2","name":"MiniMax M2.1 Lightning","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":[196608,204800],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.3,"output":2.4,"cacheRead":0.03,"official":false},"cheapest":{"provider":"llmgateway","input":0.12,"output":0.48,"cacheRead":null},"blendedRef":0.825,"blendedMin":0.21,"blendedTrusted":0.825,"spread":2.5,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/minimax-m2.1-lightning-2/"},{"id":"misc/agents-a1","name":"Agents-A1","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-26","lastUpdated":"2026-06-26","url":"https://llmpricing.dev/m/misc/agents-a1/"},{"id":"alibaba/qwen3-coder-next-fp8-no-thinking","name":"Qwen3-Coder-Next-FP8-no-thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":260000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-03","lastUpdated":"2026-02-03","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-next-fp8-no-thinking/"},{"id":"alibaba/qwen3.6-27b-fp8","name":"Qwen3.6 27B FP8","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/alibaba/qwen3.6-27b-fp8/"},{"id":"deepreinforce/ornith-1.0-35b-fp8","name":"Ornith-1.0-35B-FP8","lab":"deepreinforce","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-25","lastUpdated":"2026-06-25","url":"https://llmpricing.dev/m/deepreinforce/ornith-1.0-35b-fp8/"},{"id":"alibaba/qwen3.6-35b-a3b-fp8-no-thinking","name":"Qwen3.6-35B-A3B-fp8-no-thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-fp8-no-thinking/"},{"id":"google/gemma-4-31b-it-fp8","name":"Gemma 4 31B IT FP8","lab":"google","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-it-fp8/"},{"id":"mistral/devstral-2-123b-instruct-2512-int4-autoround","name":"Devstral-2-123B-Instruct-2512-int4-AutoRound","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"inferx","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-09","lastUpdated":"2025-12-09","url":"https://llmpricing.dev/m/mistral/devstral-2-123b-instruct-2512-int4-autoround/"},{"id":"openai/chatgpt-4o-latest","name":"OpenAI ChatGPT-4o","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":5,"output":20,"cacheRead":2.5,"official":false},"cheapest":{"provider":"helicone","input":5,"output":20,"cacheRead":2.5},"blendedRef":8.75,"blendedMin":8.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-14","lastUpdated":"2024-08-14","url":"https://llmpricing.dev/m/openai/chatgpt-4o-latest/"},{"id":"meta/llama-3.1-8b-instruct-turbo","name":"Meta Llama 3.1 8B Instruct Turbo","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.02,"output":0.03,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.02,"output":0.03,"cacheRead":null},"blendedRef":0.0225,"blendedMin":0.0225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-8b-instruct-turbo/"},{"id":"anthropic/claude-opus-4-1-20250805-4","name":"Anthropic: Claude Opus 4.1 (20250805)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"helicone","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-20250805-4/"},{"id":"xai/grok-3","name":"xAI Grok 3","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":3,"output":15,"cacheRead":0.75,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":0.75},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-01","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/xai/grok-3/"},{"id":"meta/llama-prompt-guard-2-86m","name":"Meta Llama Prompt Guard 2 86M","lab":"meta","kind":"classify","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":2,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.01,"output":0.01,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.01,"output":0.01,"cacheRead":null},"blendedRef":0.01,"blendedMin":0.01,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/meta/llama-prompt-guard-2-86m/"},{"id":"anthropic/claude-3.5-sonnet-v2","name":"Anthropic: Claude 3.5 Sonnet v2","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2024-10-22","url":"https://llmpricing.dev/m/anthropic/claude-3.5-sonnet-v2/"},{"id":"alibaba/qwen2.5-coder-7b-fast","name":"Qwen2.5 Coder 7B fast","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.03,"output":0.09,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.03,"output":0.09,"cacheRead":null},"blendedRef":0.045,"blendedMin":0.045,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-15","lastUpdated":"2024-09-15","url":"https://llmpricing.dev/m/alibaba/qwen2.5-coder-7b-fast/"},{"id":"meta/llama-prompt-guard-2-22m","name":"Meta Llama Prompt Guard 2 22M","lab":"meta","kind":"classify","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":2,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.01,"output":0.01,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.01,"output":0.01,"cacheRead":null},"blendedRef":0.01,"blendedMin":0.01,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/meta/llama-prompt-guard-2-22m/"},{"id":"openai/gpt-5-chat-latest-2","name":"OpenAI GPT-5 Chat Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003,"official":false},"cheapest":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-30","lastUpdated":"2024-09-30","url":"https://llmpricing.dev/m/openai/gpt-5-chat-latest-2/"},{"id":"openai/o3-pro-2","name":"OpenAI o3 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":20,"output":80,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":20,"output":80,"cacheRead":null},"blendedRef":35,"blendedMin":35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-01","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/openai/o3-pro-2/"},{"id":"perplexity/sonar-reasoning","name":"Perplexity Sonar Reasoning","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":127000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":1,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":1,"output":5,"cacheRead":null},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":11.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-27","lastUpdated":"2025-01-27","url":"https://llmpricing.dev/m/perplexity/sonar-reasoning/"},{"id":"perplexity/sonar-4","name":"Perplexity Sonar","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":127072,"contextRange":[127000,127072],"outputLimit":25415,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":1,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":1,"output":1,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-27","lastUpdated":"2025-01-27","url":"https://llmpricing.dev/m/perplexity/sonar-4/"},{"id":"anthropic/claude-opus-4-1-2","name":"Anthropic: Claude Opus 4.1","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"helicone","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-1-2/"},{"id":"openai/gpt-5.1-codex-mini-3","name":"OpenAI: GPT-5.1 Codex Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.25,"output":2,"cacheRead":0.024999999999999998,"official":false},"cheapest":{"provider":"helicone","input":0.25,"output":2,"cacheRead":0.024999999999999998},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex-mini-3/"},{"id":"google/gemini-2.5-flash-lite-4","name":"Google Gemini 2.5 Flash Lite","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.09999999999999999,"output":0.39999999999999997,"cacheRead":0.024999999999999998,"official":false},"cheapest":{"provider":"helicone","input":0.09999999999999999,"output":0.39999999999999997,"cacheRead":0.024999999999999998},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-22","lastUpdated":"2025-07-22","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-lite-4/"},{"id":"openai/gpt-5-codex-2","name":"OpenAI: GPT-5 Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003,"official":false},"cheapest":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/gpt-5-codex-2/"},{"id":"xai/grok-3-mini","name":"xAI Grok 3 Mini","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.3,"output":0.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"helicone","input":0.3,"output":0.5,"cacheRead":0.075},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-01","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/xai/grok-3-mini/"},{"id":"meta/hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":[8192,131072],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.14,"output":0.14,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.14,"output":0.14,"cacheRead":null},"blendedRef":0.14,"blendedMin":0.14,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-05-27","lastUpdated":"2024-06-27","url":"https://llmpricing.dev/m/meta/hermes-2-pro-llama-3-8b/"},{"id":"anthropic/claude-sonnet-4-5-20250929-5","name":"Anthropic: Claude Sonnet 4.5 (20250929)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-20250929-5/"},{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":3,"output":15,"cacheRead":0.3,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-14","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4/"},{"id":"meta/llama-guard-4","name":"Meta Llama Guard 4 12B","lab":"meta","kind":"classify","status":"ga","openWeights":false,"context":131072,"contextRange":[131072,163840],"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.21,"output":0.21,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.18,"output":0.18,"cacheRead":null},"blendedRef":0.21,"blendedMin":0.18,"blendedTrusted":null,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-04-30","url":"https://llmpricing.dev/m/meta/llama-guard-4/"},{"id":"openai/o1-mini","name":"OpenAI: o1-mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":1.1,"output":4.4,"cacheRead":0.55,"official":false},"cheapest":{"provider":"helicone","input":1.1,"output":4.4,"cacheRead":0.55},"blendedRef":1.925,"blendedMin":1.925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":14,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/o1-mini/"},{"id":"openai/gpt-4.1-nano-4","name":"OpenAI GPT-4.1 Nano","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.09999999999999999,"output":0.39999999999999997,"cacheRead":0.024999999999999998,"official":false},"cheapest":{"provider":"helicone","input":0.09999999999999999,"output":0.39999999999999997,"cacheRead":0.024999999999999998},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-nano-4/"},{"id":"meta/llama-3.1-8b-instruct-3","name":"Meta Llama 3.1 8B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.02,"output":0.049999999999999996,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.02,"output":0.049999999999999996,"cacheRead":null},"blendedRef":0.0275,"blendedMin":0.0275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-8b-instruct-3/"},{"id":"meta/llama-4-maverick-2","name":"Meta Llama 4 Maverick 17B 128E","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/meta/llama-4-maverick-2/"},{"id":"google/gemma2-9b-it","name":"Google Gemma 2","lab":"google","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.01,"output":0.03,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.01,"output":0.03,"cacheRead":null},"blendedRef":0.015,"blendedMin":0.015,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-25","lastUpdated":"2024-06-25","url":"https://llmpricing.dev/m/google/gemma2-9b-it/"},{"id":"xai/grok-4-4","name":"xAI Grok 4","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":3,"output":15,"cacheRead":0.75,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":0.75},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-09","lastUpdated":"2024-07-09","url":"https://llmpricing.dev/m/xai/grok-4-4/"},{"id":"openai/gpt-5-pro-3","name":"OpenAI: GPT-5 Pro","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":15,"output":120,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":15,"output":120,"cacheRead":null},"blendedRef":41.25,"blendedMin":41.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/gpt-5-pro-3/"},{"id":"perplexity/sonar-reasoning-pro-4","name":"Perplexity Sonar Reasoning Pro","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[127000,128000],"outputLimit":25600,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":2,"output":8,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":2,"output":8,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-27","lastUpdated":"2025-03-07","url":"https://llmpricing.dev/m/perplexity/sonar-reasoning-pro-4/"},{"id":"google/gemini-2.5-flash-4","name":"Google Gemini 2.5 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.3,"output":2.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"helicone","input":0.3,"output":2.5,"cacheRead":0.075},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-4/"},{"id":"google/gemini-3-pro-preview-2","name":"Google Gemini 3 Pro Preview","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","audio","video"],"reference":{"provider":"helicone","input":2,"output":12,"cacheRead":0.19999999999999998,"official":false},"cheapest":{"provider":"helicone","input":2,"output":12,"cacheRead":0.19999999999999998},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-18","lastUpdated":"2025-11-18","url":"https://llmpricing.dev/m/google/gemini-3-pro-preview-2/"},{"id":"meta/llama-3.3-70b-versatile","name":"Meta Llama 3.3 70B Versatile","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32678,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.59,"output":0.7899999999999999,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.59,"output":0.7899999999999999,"cacheRead":null},"blendedRef":0.64,"blendedMin":0.64,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-versatile/"},{"id":"anthropic/claude-haiku-4-5-20251001-5","name":"Anthropic: Claude 4.5 Haiku (20251001)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1,"output":5,"cacheRead":0.09999999999999999,"official":false},"cheapest":{"provider":"helicone","input":1,"output":5,"cacheRead":0.09999999999999999},"blendedRef":2,"blendedMin":2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-01","lastUpdated":"2025-10-01","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-20251001-5/"},{"id":"perplexity/sonar-pro-4","name":"Perplexity Sonar Pro","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-27","lastUpdated":"2025-03-07","url":"https://llmpricing.dev/m/perplexity/sonar-pro-4/"},{"id":"meta/llama-4-scout-2","name":"Meta Llama 4 Scout 17B 16E","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.08,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.08,"output":0.3,"cacheRead":null},"blendedRef":0.135,"blendedMin":0.135,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/meta/llama-4-scout-2/"},{"id":"openai/gpt-4.1-mini-2025-04-14","name":"OpenAI GPT-4.1 Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.39999999999999997,"output":1.5999999999999999,"cacheRead":0.09999999999999999,"official":false},"cheapest":{"provider":"helicone","input":0.39999999999999997,"output":1.5999999999999999,"cacheRead":0.09999999999999999},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-mini-2025-04-14/"},{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":15,"output":75,"cacheRead":1.5,"official":false},"cheapest":{"provider":"helicone","input":15,"output":75,"cacheRead":1.5},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-14","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-opus-4/"},{"id":"openai/gpt-5.1-chat-latest-3","name":"OpenAI GPT-5.1 Chat","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003,"official":false},"cheapest":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/gpt-5.1-chat-latest-3/"},{"id":"meta/llama-3.1-8b-instant","name":"Meta Llama 3.1 8B Instant","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32678,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.049999999999999996,"output":0.08,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.049999999999999996,"output":0.08,"cacheRead":null},"blendedRef":0.0575,"blendedMin":0.0575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/meta/llama-3.1-8b-instant/"},{"id":"anthropic/claude-3.5-haiku-2","name":"Anthropic: Claude 3.5 Haiku","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":0.7999999999999999,"output":4,"cacheRead":0.08,"official":false},"cheapest":{"provider":"helicone","input":0.7999999999999999,"output":4,"cacheRead":0.08},"blendedRef":1.6,"blendedMin":1.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2024-10-22","url":"https://llmpricing.dev/m/anthropic/claude-3.5-haiku-2/"},{"id":"openai/gpt-5.1-codex-3","name":"OpenAI: GPT-5.1 Codex","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003,"official":false},"cheapest":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/gpt-5.1-codex-3/"},{"id":"google/gemini-2.5-pro-4","name":"Google Gemini 2.5 Pro","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.3125,"official":false},"cheapest":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.3125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-4/"},{"id":"deepseek/deepseek-tng-r1t2-chimera","name":"DeepSeek TNG R1T2 Chimera","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":130000,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.3,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.3,"output":1.2,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-02","lastUpdated":"2025-07-02","url":"https://llmpricing.dev/m/deepseek/deepseek-tng-r1t2-chimera/"},{"id":"anthropic/claude-4.5-sonnet","name":"Anthropic: Claude Sonnet 4.5","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004,"official":false},"cheapest":{"provider":"helicone","input":3,"output":15,"cacheRead":0.30000000000000004},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-4.5-sonnet/"},{"id":"baidu/ernie-4.5-21b-a3b-thinking","name":"Baidu Ernie 4.5 21B A3B Thinking","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"helicone","input":0.07,"output":0.28,"cacheRead":null,"official":false},"cheapest":{"provider":"helicone","input":0.07,"output":0.28,"cacheRead":null},"blendedRef":0.1225,"blendedMin":0.1225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-16","lastUpdated":"2025-03-16","url":"https://llmpricing.dev/m/baidu/ernie-4.5-21b-a3b-thinking/"},{"id":"openai/gpt-5.1-4","name":"OpenAI GPT-5.1","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003,"official":false},"cheapest":{"provider":"helicone","input":1.25,"output":10,"cacheRead":0.12500000000000003},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/openai/gpt-5.1-4/"},{"id":"openai/kb-whisper-large","name":"KB Whisper","lab":"openai","kind":"audio","status":"ga","openWeights":true,"context":448,"contextRange":null,"outputLimit":448,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null,"official":false},"cheapest":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null},"blendedRef":0.0023,"blendedMin":0.0023,"blendedTrusted":0.0023,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/kb-whisper-large/"},{"id":"openai/multilingual-e5-large-instruct","name":"E5 Multi-Lingual Large Embeddings 0.6B","lab":"openai","kind":"embedding","status":"ga","openWeights":true,"context":512,"contextRange":null,"outputLimit":512,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"evroc","input":0.114,"output":0.114,"cacheRead":null,"official":false},"cheapest":{"provider":"evroc","input":0.114,"output":0.114,"cacheRead":null},"blendedRef":0.114,"blendedMin":0.114,"blendedTrusted":0.114,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-01","lastUpdated":"2024-06-01","url":"https://llmpricing.dev/m/openai/multilingual-e5-large-instruct/"},{"id":"openai/whisper-large-v3-2","name":"Whisper 3 Large","lab":"openai","kind":"audio","status":"ga","openWeights":true,"context":448,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null,"official":false},"cheapest":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null},"blendedRef":0.0023,"blendedMin":0.0023,"blendedTrusted":0.0023,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/whisper-large-v3-2/"},{"id":"openai/whisper-large-v3-turbo","name":"Whisper Large v3 Turbo","lab":"openai","kind":"audio","status":"ga","openWeights":true,"context":448,"contextRange":null,"outputLimit":448,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null,"official":false},"cheapest":{"provider":"evroc","input":0.0023,"output":0.0023,"cacheRead":null},"blendedRef":0.0023,"blendedMin":0.0023,"blendedTrusted":0.0023,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-01","url":"https://llmpricing.dev/m/openai/whisper-large-v3-turbo/"},{"id":"evroc/roc","name":"roc","lab":"evroc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"evroc","input":2.875,"output":11.516,"cacheRead":null,"official":true},"cheapest":{"provider":"evroc","input":2.875,"output":11.516,"cacheRead":null},"blendedRef":5.0352,"blendedMin":5.0352,"blendedTrusted":5.0352,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-06","lastUpdated":"2026-06-06","url":"https://llmpricing.dev/m/evroc/roc/"},{"id":"anthropic/claude-mythos-5","name":"Claude Mythos 5","lab":"anthropic","kind":"text","status":"beta","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"azure","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":20,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/claude-mythos-5/"},{"id":"mistral/mistral-small-2503","name":"Mistral Small 3.1","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"azure","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":14.9,"coding":26.3,"agentic":5.3,"speed":149,"ttft":0.81,"taskCost":0.0443},"usage":null,"releaseDate":"2025-03-01","lastUpdated":"2025-03-01","url":"https://llmpricing.dev/m/mistral/mistral-small-2503/"},{"id":"openai/gpt-4-turbo-vision","name":"GPT-4 Turbo Vision","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"azure","input":10,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":10,"output":30,"cacheRead":null},"blendedRef":15,"blendedMin":15,"blendedTrusted":15,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2024-04-09","url":"https://llmpricing.dev/m/openai/gpt-4-turbo-vision/"},{"id":"cohere/cohere-embed-v3-multilingual","name":"Embed v3 Multilingual","lab":"cohere","kind":"embedding","status":"ga","openWeights":true,"context":512,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure","input":0.1,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.1,"output":0,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":0.075,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2023-11-07","lastUpdated":"2023-11-07","url":"https://llmpricing.dev/m/cohere/cohere-embed-v3-multilingual/"},{"id":"misc/model-router","name":"Model Router","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"azure","input":0.14,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.14,"output":0,"cacheRead":null},"blendedRef":0.105,"blendedMin":0.105,"blendedTrusted":0.105,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-19","lastUpdated":"2025-11-18","url":"https://llmpricing.dev/m/misc/model-router/"},{"id":"microsoft/phi-4-reasoning","name":"Phi-4-reasoning","lab":"microsoft","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure-cognitive-services","input":0.125,"output":0.5,"cacheRead":null,"official":true},"cheapest":{"provider":"azure-cognitive-services","input":0.125,"output":0.5,"cacheRead":null},"blendedRef":0.2188,"blendedMin":0.2188,"blendedTrusted":0.2188,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2024-12-11","url":"https://llmpricing.dev/m/microsoft/phi-4-reasoning/"},{"id":"microsoft/phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","lab":"microsoft","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure-cognitive-services","input":0.075,"output":0.3,"cacheRead":null,"official":true},"cheapest":{"provider":"azure-cognitive-services","input":0.075,"output":0.3,"cacheRead":null},"blendedRef":0.1312,"blendedMin":0.1312,"blendedTrusted":0.1312,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2024-12-11","url":"https://llmpricing.dev/m/microsoft/phi-4-mini-reasoning/"},{"id":"cohere/cohere-embed-v3-english","name":"Embed v3 English","lab":"cohere","kind":"embedding","status":"ga","openWeights":true,"context":512,"contextRange":null,"outputLimit":1024,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure","input":0.1,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.1,"output":0,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":0.075,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2023-11-07","lastUpdated":"2023-11-07","url":"https://llmpricing.dev/m/cohere/cohere-embed-v3-english/"},{"id":"openai/gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo 0125","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure","input":0.5,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":0.75,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-0125/"},{"id":"openai/codex-mini","name":"Codex Mini","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"azure","input":1.5,"output":6,"cacheRead":0.375,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":1.5,"output":6,"cacheRead":0.375},"blendedRef":2.625,"blendedMin":2.625,"blendedTrusted":2.625,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-16","lastUpdated":"2025-05-16","url":"https://llmpricing.dev/m/openai/codex-mini/"},{"id":"openai/gpt-3.5-turbo-1106","name":"GPT-3.5 Turbo 1106","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure","input":1,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":1,"output":2,"cacheRead":null},"blendedRef":1.25,"blendedMin":1.25,"blendedTrusted":1.25,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-1106/"},{"id":"cohere/cohere-embed-v-4-0","name":"Embed v4","lab":"cohere","kind":"embedding","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"azure","input":0.12,"output":0,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.12,"output":0,"cacheRead":null},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":0.09,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/cohere/cohere-embed-v-4-0/"},{"id":"mistral/codestral-2501","name":"Codestral 25.01","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure","input":0.3,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.3,"output":0.9,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":0.45,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-01-01","lastUpdated":"2025-01-01","url":"https://llmpricing.dev/m/mistral/codestral-2501/"},{"id":"deepseek/deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure","input":0.58,"output":1.68,"cacheRead":null,"official":false},"cheapest":{"provider":"azure-cognitive-services","input":0.58,"output":1.68,"cacheRead":null},"blendedRef":0.855,"blendedMin":0.855,"blendedTrusted":0.855,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":22.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-speciale/"},{"id":"microsoft/phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","lab":"microsoft","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"azure-cognitive-services","input":0.125,"output":0.5,"cacheRead":null,"official":true},"cheapest":{"provider":"azure-cognitive-services","input":0.125,"output":0.5,"cacheRead":null},"blendedRef":0.2188,"blendedMin":0.2188,"blendedTrusted":0.2188,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-11","lastUpdated":"2024-12-11","url":"https://llmpricing.dev/m/microsoft/phi-4-reasoning-plus/"},{"id":"misc/claude-sonnet-4-5-20250929-thinking","name":"claude-sonnet-4-5-20250929-thinking","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/misc/claude-sonnet-4-5-20250929-thinking/"},{"id":"alibaba/qwen-max-latest","name":"Qwen-Max-Latest","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"302ai","input":0.343,"output":1.372,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.343,"output":1.372,"cacheRead":null},"blendedRef":0.6003,"blendedMin":0.6003,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-03","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-max-latest/"},{"id":"misc/doubao-seed-1-8-251215","name":"doubao-seed-1-8-251215","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":224000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.114,"output":0.286,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.114,"output":0.286,"cacheRead":null},"blendedRef":0.157,"blendedMin":0.157,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/misc/doubao-seed-1-8-251215/"},{"id":"openai/chatgpt-4o-latest-2","name":"chatgpt-4o-latest","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":5,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":4.5,"output":14,"cacheRead":null},"blendedRef":7.5,"blendedMin":6.875,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-08-08","lastUpdated":"2024-08-14","url":"https://llmpricing.dev/m/openai/chatgpt-4o-latest-2/"},{"id":"misc/gemini-3-pro-image-preview","name":"gemini-3-pro-image-preview","lab":"misc","kind":"image","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":2,"output":120,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":2,"output":120,"cacheRead":null},"blendedRef":31.5,"blendedMin":31.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-20","lastUpdated":"2025-11-20","url":"https://llmpricing.dev/m/misc/gemini-3-pro-image-preview/"},{"id":"misc/grok-4.20-beta-0309-reasoning","name":"grok-4.20-beta-0309-reasoning","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":2,"output":6,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":2,"output":6,"cacheRead":null},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/misc/grok-4.20-beta-0309-reasoning/"},{"id":"anthropic/claude-3-5-haiku-latest","name":"claude-3-5-haiku-latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":0.8,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.8,"output":4,"cacheRead":null},"blendedRef":1.6,"blendedMin":1.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2024-10-22","url":"https://llmpricing.dev/m/anthropic/claude-3-5-haiku-latest/"},{"id":"zhipuai/glm-4.5-x-2","name":"glm-4.5-x","lab":"zhipuai","kind":"text","status":"beta","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":2.2,"output":8.9,"cacheRead":0.45,"official":false},"cheapest":{"provider":"302ai","input":1.143,"output":2.29,"cacheRead":null},"blendedRef":3.875,"blendedMin":1.4298,"blendedTrusted":null,"spread":1.9,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-29","lastUpdated":"2025-07-29","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-x-2/"},{"id":"anthropic/claude-3-5-haiku-20241022","name":"claude-3-5-haiku-20241022","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":0.8,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.8,"output":4,"cacheRead":null},"blendedRef":1.6,"blendedMin":1.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2024-10-22","url":"https://llmpricing.dev/m/anthropic/claude-3-5-haiku-20241022/"},{"id":"misc/doubao-seed-1-6-thinking-250715","name":"doubao-seed-1-6-thinking-250715","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.121,"output":1.21,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.121,"output":1.21,"cacheRead":null},"blendedRef":0.3933,"blendedMin":0.3933,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-15","lastUpdated":"2025-07-15","url":"https://llmpricing.dev/m/misc/doubao-seed-1-6-thinking-250715/"},{"id":"misc/grok-4.20-beta-0309-non-reasoning","name":"grok-4.20-beta-0309-non-reasoning","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":2,"output":6,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":2,"output":6,"cacheRead":null},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/misc/grok-4.20-beta-0309-non-reasoning/"},{"id":"misc/gpt-5-thinking","name":"gpt-5-thinking","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":1.25,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":1.25,"output":10,"cacheRead":null},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-08","lastUpdated":"2025-08-08","url":"https://llmpricing.dev/m/misc/gpt-5-thinking/"},{"id":"openai/gpt-5.4-nano-2026-03-17","name":"gpt-5.4-nano-2026-03-17","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.2,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.2,"output":1.25,"cacheRead":null},"blendedRef":0.4625,"blendedMin":0.4625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-19","lastUpdated":"2026-03-19","url":"https://llmpricing.dev/m/openai/gpt-5.4-nano-2026-03-17/"},{"id":"google/gemini-2.5-flash-nothink","name":"gemini-2.5-flash-nothink","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.3,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.3,"output":2.5,"cacheRead":null},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-24","lastUpdated":"2025-06-24","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-nothink/"},{"id":"misc/doubao-seed-1-6-vision-250815","name":"doubao-seed-1-6-vision-250815","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.114,"output":1.143,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.114,"output":1.143,"cacheRead":null},"blendedRef":0.3713,"blendedMin":0.3713,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/misc/doubao-seed-1-6-vision-250815/"},{"id":"misc/claude-opus-4-1-20250805-thinking","name":"claude-opus-4-1-20250805-thinking","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":15,"output":75,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":15,"output":75,"cacheRead":null},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-27","lastUpdated":"2025-05-27","url":"https://llmpricing.dev/m/misc/claude-opus-4-1-20250805-thinking/"},{"id":"misc/mistral-large-2512","name":"mistral-large-2512","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":1.1,"output":3.3,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":1.1,"output":3.3,"cacheRead":null},"blendedRef":1.65,"blendedMin":1.65,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/misc/mistral-large-2512/"},{"id":"misc/grok-4.20-multi-agent-beta-0309","name":"grok-4.20-multi-agent-beta-0309","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":30000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":2,"output":6,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":2,"output":6,"cacheRead":null},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/misc/grok-4.20-multi-agent-beta-0309/"},{"id":"zhipuai/glm-4.5-airx-2","name":"glm-4.5-airx","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":1.1,"output":4.5,"cacheRead":0.22,"official":false},"cheapest":{"provider":"302ai","input":0.572,"output":1.714,"cacheRead":null},"blendedRef":1.95,"blendedMin":0.8575,"blendedTrusted":null,"spread":1.9,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-29","lastUpdated":"2025-07-29","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-airx-2/"},{"id":"misc/grok-4.1","name":"grok-4.1","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":2,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":2,"output":10,"cacheRead":null},"blendedRef":4,"blendedMin":4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-18","lastUpdated":"2025-11-18","url":"https://llmpricing.dev/m/misc/grok-4.1/"},{"id":"openai/gpt-5.4-mini-2026-03-17","name":"gpt-5.4-mini-2026-03-17","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.75,"output":4.5,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.75,"output":4.5,"cacheRead":null},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-19","lastUpdated":"2026-03-19","url":"https://llmpricing.dev/m/openai/gpt-5.4-mini-2026-03-17/"},{"id":"misc/kimi-k2-0905-preview","name":"kimi-k2-0905-preview","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"302ai","input":0.632,"output":2.53,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.632,"output":2.53,"cacheRead":null},"blendedRef":1.1065,"blendedMin":1.1065,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-05","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/misc/kimi-k2-0905-preview/"},{"id":"misc/claude-opus-4-5-20251101-thinking","name":"claude-opus-4-5-20251101-thinking","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":5,"output":25,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":5,"output":25,"cacheRead":null},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-25","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/misc/claude-opus-4-5-20251101-thinking/"},{"id":"misc/gemini-3.1-flash-image-preview","name":"gemini-3.1-flash-image-preview","lab":"misc","kind":"image","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"302ai","input":0.5,"output":60,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.5,"output":60,"cacheRead":null},"blendedRef":15.375,"blendedMin":15.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-27","lastUpdated":"2026-02-27","url":"https://llmpricing.dev/m/misc/gemini-3.1-flash-image-preview/"},{"id":"zhipuai/glm-for-coding","name":"glm-for-coding","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"302ai","input":0.086,"output":0.343,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.086,"output":0.343,"cacheRead":null},"blendedRef":0.1503,"blendedMin":0.1503,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-30","lastUpdated":"2025-09-30","url":"https://llmpricing.dev/m/zhipuai/glm-for-coding/"},{"id":"anthropic/claude-opus-4-6-thinking","name":"claude-opus-4-6-thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"aihubmix","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"302ai","input":5,"output":25,"cacheRead":null},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-06","lastUpdated":"2026-03-13","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-6-thinking/"},{"id":"misc/qwen3-max-2025-09-23","name":"qwen3-max-2025-09-23","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":258048,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"302ai","input":0.86,"output":3.43,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.86,"output":3.43,"cacheRead":null},"blendedRef":1.5025,"blendedMin":1.5025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-24","lastUpdated":"2025-09-24","url":"https://llmpricing.dev/m/misc/qwen3-max-2025-09-23/"},{"id":"misc/doubao-seed-code-preview-251028","name":"doubao-seed-code-preview-251028","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"302ai","input":0.17,"output":1.14,"cacheRead":null,"official":false},"cheapest":{"provider":"302ai","input":0.17,"output":1.14,"cacheRead":null},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-11","lastUpdated":"2025-11-11","url":"https://llmpricing.dev/m/misc/doubao-seed-code-preview-251028/"},{"id":"google/gemini-3-pro","name":"Gemini 3 Pro","lab":"google","kind":"text","status":"deprecated","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"opencode","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"poe","input":1.6,"output":9.6,"cacheRead":0.16},"blendedRef":4.5,"blendedMin":3.6,"blendedTrusted":null,"spread":1.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-11-18","lastUpdated":"2025-11-18","url":"https://llmpricing.dev/m/google/gemini-3-pro/"},{"id":"misc/ling-3.0-flash-free","name":"Ling-3.0-flash Free","lab":"misc","kind":"text","status":"deprecated","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-23","lastUpdated":"2026-07-23","url":"https://llmpricing.dev/m/misc/ling-3.0-flash-free/"},{"id":"misc/ring-2.6-1t-free","name":"Ring 2.6 1T Free","lab":"misc","kind":"text","status":"deprecated","openWeights":true,"context":262000,"contextRange":null,"outputLimit":66000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-08","lastUpdated":"2026-05-08","url":"https://llmpricing.dev/m/misc/ring-2.6-1t-free/"},{"id":"moonshotai/kimi-k2.5-free","name":"Kimi K2.5 Free","lab":"moonshotai","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-free/"},{"id":"minimax/minimax-m3-free","name":"MiniMax-M3 Free","lab":"minimax","kind":"text","status":"deprecated","openWeights":true,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-31","lastUpdated":"2026-05-31","url":"https://llmpricing.dev/m/minimax/minimax-m3-free/"},{"id":"openai/gpt-5.6-sol-5","name":"GPT-5.6 Sol (50% Off)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"opencode","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"opencode","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-5/"},{"id":"zhipuai/glm-4.7-free","name":"GLM-4.7 Free","lab":"zhipuai","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/zhipuai/glm-4.7-free/"},{"id":"arcee-ai/trinity-large-preview","name":"Trinity Large Preview","lab":"arcee-ai","kind":"text","status":"deprecated","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/arcee-ai/trinity-large-preview/"},{"id":"anthropic/claude-3-5-haiku-20241022-2","name":"Claude Haiku 3.5","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":200000,"contextRange":[189096,200000],"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"opencode","input":0.8,"output":4,"cacheRead":0.08,"official":false},"cheapest":{"provider":"poe","input":0.68,"output":3.4,"cacheRead":0.068},"blendedRef":1.6,"blendedMin":1.36,"blendedTrusted":null,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-10-22","lastUpdated":"2024-10-22","url":"https://llmpricing.dev/m/anthropic/claude-3-5-haiku-20241022-2/"},{"id":"tencent/hy3-preview-free","name":"Hy3 preview Free","lab":"tencent","kind":"text","status":"deprecated","openWeights":true,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-20","lastUpdated":"2026-04-20","url":"https://llmpricing.dev/m/tencent/hy3-preview-free/"},{"id":"tencent/hy3-free","name":"Hy3 Free","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":190000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3-free/"},{"id":"misc/muse-spark-1.2-contributor-free","name":"Muse Spark 1.2 Free","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","pdf","audio"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-05","lastUpdated":"2026-08-05","url":"https://llmpricing.dev/m/misc/muse-spark-1.2-contributor-free/"},{"id":"misc/x-preview-f-free","name":"Ox Alpha Free","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-21","lastUpdated":"2026-08-21","url":"https://llmpricing.dev/m/misc/x-preview-f-free/"},{"id":"misc/ling-2.6-flash-free","name":"Ling 2.6 Flash Free","lab":"misc","kind":"text","status":"deprecated","openWeights":true,"context":262100,"contextRange":null,"outputLimit":32800,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/misc/ling-2.6-flash-free/"},{"id":"misc/mimo-v2-pro-free","name":"MiMo V2 Pro Free","lab":"misc","kind":"text","status":"deprecated","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/misc/mimo-v2-pro-free/"},{"id":"misc/mimo-v2-flash-free","name":"MiMo V2 Flash Free","lab":"misc","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/misc/mimo-v2-flash-free/"},{"id":"minimax/minimax-m2.5-free","name":"MiniMax-M2.5 Free","lab":"minimax","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-free/"},{"id":"zhipuai/glm-5-free","name":"GLM-5 Free","lab":"zhipuai","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-11","lastUpdated":"2026-02-11","url":"https://llmpricing.dev/m/zhipuai/glm-5-free/"},{"id":"alibaba/qwen3.6-plus-free","name":"Qwen3.6 Plus Free","lab":"alibaba","kind":"text","status":"deprecated","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/alibaba/qwen3.6-plus-free/"},{"id":"minimax/minimax-m2.1-free","name":"MiniMax-M2.1 Free","lab":"minimax","kind":"text","status":"deprecated","openWeights":true,"context":204800,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/minimax/minimax-m2.1-free/"},{"id":"google/gemini-3-flash","name":"Gemini 3 Flash","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":[1000000,1048576],"outputLimit":65000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"vercel","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"poe","input":0.4,"output":2.4,"cacheRead":0.04},"blendedRef":1.125,"blendedMin":0.9,"blendedTrusted":1.125,"spread":1.3,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-12-17","lastUpdated":"2025-12-17","url":"https://llmpricing.dev/m/google/gemini-3-flash/"},{"id":"misc/ling-3.0-tiny-free","name":"Ling-3.0-tiny Free","lab":"misc","kind":"text","status":"deprecated","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-06","lastUpdated":"2026-08-06","url":"https://llmpricing.dev/m/misc/ling-3.0-tiny-free/"},{"id":"misc/big-pickle","name":"Big Pickle","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-17","lastUpdated":"2025-10-17","url":"https://llmpricing.dev/m/misc/big-pickle/"},{"id":"misc/mimo-v2-omni-free","name":"MiMo V2 Omni Free","lab":"misc","kind":"text","status":"deprecated","openWeights":true,"context":262144,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","pdf"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/misc/mimo-v2-omni-free/"},{"id":"meituan/longcat-2.0-free","name":"LongCat-2.0 Free","lab":"meituan","kind":"text","status":"deprecated","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"opencode","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/meituan/longcat-2.0-free/"},{"id":"anthropic/claude-sonnet-4-5-eu","name":"Claude Sonnet 4.5 (latest) (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":2.97,"output":14.85,"cacheRead":0.27,"official":false},"cheapest":{"provider":"requesty","input":2.97,"output":14.85,"cacheRead":0.27},"blendedRef":5.94,"blendedMin":5.94,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-09-29","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-5-eu/"},{"id":"openai/gpt-5.1-eu","name":"GPT-5.1 (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":1.2375,"output":9.9,"cacheRead":0.12375,"official":false},"cheapest":{"provider":"requesty","input":1.2375,"output":9.9,"cacheRead":0.12375},"blendedRef":3.4031,"blendedMin":3.4031,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/openai/gpt-5.1-eu/"},{"id":"openai/gpt-4.1-nano-eu","name":"GPT-4.1 nano (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":0.099,"output":0.396,"cacheRead":0.02475,"official":false},"cheapest":{"provider":"requesty","input":0.099,"output":0.396,"cacheRead":0.02475},"blendedRef":0.1733,"blendedMin":0.1733,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-nano-eu/"},{"id":"google/gemini-2.5-flash-eu","name":"Gemini 2.5 Flash (EU)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio","video","pdf"],"reference":{"provider":"requesty","input":0.27,"output":2.25,"cacheRead":0.0675,"official":false},"cheapest":{"provider":"requesty","input":0.27,"output":2.25,"cacheRead":0.0675},"blendedRef":0.765,"blendedMin":0.765,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-eu/"},{"id":"nvidia/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-content-safety/"},{"id":"alibaba/thinkingcap-qwen3.6-27b-eu","name":"thinkingcap-qwen3.6-27b@eu","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.36,"output":2.7,"cacheRead":0.234,"official":false},"cheapest":{"provider":"requesty","input":0.36,"output":2.7,"cacheRead":0.234},"blendedRef":0.945,"blendedMin":0.945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-13","lastUpdated":"2026-07-13","url":"https://llmpricing.dev/m/alibaba/thinkingcap-qwen3.6-27b-eu/"},{"id":"mistral/mistral-medium-latest-eu","name":"Mistral Medium (latest) (EU)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396,"official":false},"cheapest":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396},"blendedRef":0.792,"blendedMin":0.792,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-29","lastUpdated":"2026-04-29","url":"https://llmpricing.dev/m/mistral/mistral-medium-latest-eu/"},{"id":"zhipuai/glm-5.2-eu","name":"GLM-5.2 (EU)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":1.08,"output":3.78,"cacheRead":0.234,"official":false},"cheapest":{"provider":"requesty","input":1.08,"output":3.78,"cacheRead":0.234},"blendedRef":1.755,"blendedMin":1.755,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-eu/"},{"id":"openai/gpt-5.6-sol-eu","name":"GPT-5.6 Sol (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":4.95,"output":29.7,"cacheRead":0.495,"official":false},"cheapest":{"provider":"requesty","input":4.95,"output":29.7,"cacheRead":0.495},"blendedRef":11.1375,"blendedMin":11.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-eu/"},{"id":"openai/gpt-5-mini-eu","name":"GPT-5 Mini (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":0.2475,"output":1.98,"cacheRead":0.02475,"official":false},"cheapest":{"provider":"requesty","input":0.2475,"output":1.98,"cacheRead":0.02475},"blendedRef":0.6806,"blendedMin":0.6806,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-mini-eu/"},{"id":"deepseek/deepseek-v4-pro-eu","name":"DeepSeek V4 Pro (EU)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":1.575,"output":3.15,"cacheRead":0.396,"official":false},"cheapest":{"provider":"requesty","input":1.575,"output":3.15,"cacheRead":0.396},"blendedRef":1.9688,"blendedMin":1.9688,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-eu/"},{"id":"misc/leanstral-1-5-eu","name":"leanstral-1-5@eu","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-27","lastUpdated":"2026-05-27","url":"https://llmpricing.dev/m/misc/leanstral-1-5-eu/"},{"id":"google/gemini-3.1-flash-lite-eu","name":"Gemini 3.1 Flash Lite (EU)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"requesty","input":0.2475,"output":1.485,"cacheRead":0.02475,"official":false},"cheapest":{"provider":"requesty","input":0.2475,"output":1.485,"cacheRead":0.02475},"blendedRef":0.5569,"blendedMin":0.5569,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite-eu/"},{"id":"openai/gpt-5-eu","name":"GPT-5 (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":1.2375,"output":9.9,"cacheRead":0.12375,"official":false},"cheapest":{"provider":"requesty","input":1.2375,"output":9.9,"cacheRead":0.12375},"blendedRef":3.4031,"blendedMin":3.4031,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-eu/"},{"id":"openai/gpt-5.5-eu","name":"GPT-5.5 (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":4.5,"output":27,"cacheRead":0.45,"official":false},"cheapest":{"provider":"requesty","input":4.5,"output":27,"cacheRead":0.45},"blendedRef":10.125,"blendedMin":10.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5-eu/"},{"id":"moonshotai/kimi-k2.6-eu","name":"Kimi K2.6 (EU)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"requesty","input":0.855,"output":3.6,"cacheRead":0.855,"official":false},"cheapest":{"provider":"requesty","input":0.855,"output":3.6,"cacheRead":0.855},"blendedRef":1.5413,"blendedMin":1.5413,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-eu/"},{"id":"openai/gpt-5.6-luna-eu","name":"GPT-5.6 Luna (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":0.198,"output":1.188,"cacheRead":0.0198,"official":false},"cheapest":{"provider":"requesty","input":0.198,"output":1.188,"cacheRead":0.0198},"blendedRef":0.4455,"blendedMin":0.4455,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna-eu/"},{"id":"nvidia/nemotron-3-ultra-nvfp4","name":"nemotron-3-ultra-nvfp4","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.54,"output":2.16,"cacheRead":0.108,"official":false},"cheapest":{"provider":"requesty","input":0.54,"output":2.16,"cacheRead":0.108},"blendedRef":0.945,"blendedMin":0.945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-nvfp4/"},{"id":"openai/gpt-5-nano-eu","name":"GPT-5 Nano (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":0.0495,"output":0.396,"cacheRead":0.00495,"official":false},"cheapest":{"provider":"requesty","input":0.0495,"output":0.396,"cacheRead":0.00495},"blendedRef":0.1361,"blendedMin":0.1361,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-nano-eu/"},{"id":"openai/gpt-4.1-mini-eu","name":"GPT-4.1 mini (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":0.396,"output":1.584,"cacheRead":0.099,"official":false},"cheapest":{"provider":"requesty","input":0.396,"output":1.584,"cacheRead":0.099},"blendedRef":0.693,"blendedMin":0.693,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-mini-eu/"},{"id":"openai/o4-mini-eu","name":"o4-mini (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":1.089,"output":4.356,"cacheRead":0.27225,"official":false},"cheapest":{"provider":"requesty","input":1.089,"output":4.356,"cacheRead":0.27225},"blendedRef":1.9058,"blendedMin":1.9058,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-eu/"},{"id":"moonshotai/kimi-k3-eu","name":"Kimi K3 (EU)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"requesty","input":2.025,"output":10.125,"cacheRead":0.2025,"official":false},"cheapest":{"provider":"requesty","input":2.025,"output":10.125,"cacheRead":0.2025},"blendedRef":4.05,"blendedMin":4.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-eu/"},{"id":"mistral/devstral-latest","name":"devstral-latest","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396,"official":false},"cheapest":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396},"blendedRef":0.792,"blendedMin":0.792,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-27","lastUpdated":"2026-05-27","url":"https://llmpricing.dev/m/mistral/devstral-latest/"},{"id":"nvidia/nemotron-lightning-3.5-30b-a3b","name":"nemotron-lightning-3.5-30b-a3b","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.045,"output":0.18,"cacheRead":0.009,"official":false},"cheapest":{"provider":"requesty","input":0.045,"output":0.18,"cacheRead":0.009},"blendedRef":0.0788,"blendedMin":0.0788,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-15","lastUpdated":"2026-08-15","url":"https://llmpricing.dev/m/nvidia/nemotron-lightning-3.5-30b-a3b/"},{"id":"thinkingmachines/inkling-256k","name":"inkling-256k","lab":"thinkingmachines","kind":"video","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"thinkingmachines","input":3.74,"output":9.36,"cacheRead":0.748,"official":true},"cheapest":{"provider":"requesty","input":1.496,"output":3.744,"cacheRead":0.2992},"blendedRef":5.145,"blendedMin":2.058,"blendedTrusted":5.145,"spread":2.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/thinkingmachines/inkling-256k/"},{"id":"moonshotai/kimi-k2.7-code-eu","name":"Kimi K2.7 Code (EU)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"requesty","input":1.125,"output":4.05,"cacheRead":0.279,"official":false},"cheapest":{"provider":"requesty","input":1.125,"output":4.05,"cacheRead":0.279},"blendedRef":1.8563,"blendedMin":1.8563,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.7-code-eu/"},{"id":"google/gemini-3.5-flash-eu","name":"Gemini 3.5 Flash (EU)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":1.5,"output":9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"requesty","input":1.485,"output":8.91,"cacheRead":0.1485},"blendedRef":3.375,"blendedMin":3.3413,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-eu/"},{"id":"xai/grok-4.2-beta","name":"grok-4.2-beta","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":1.8,"output":5.4,"cacheRead":0.18,"official":false},"cheapest":{"provider":"requesty","input":1.8,"output":5.4,"cacheRead":0.18},"blendedRef":2.7,"blendedMin":2.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-19","lastUpdated":"2026-03-19","url":"https://llmpricing.dev/m/xai/grok-4.2-beta/"},{"id":"mistral/mistral-small-2603-eu","name":"Mistral Small 4 (EU)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":0.1485,"output":0.594,"cacheRead":0.1485,"official":false},"cheapest":{"provider":"requesty","input":0.1485,"output":0.594,"cacheRead":0.1485},"blendedRef":0.2599,"blendedMin":0.2599,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/mistral/mistral-small-2603-eu/"},{"id":"kwaipilot/kat-coder-pro","name":"kat-coder-pro","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"requesty","input":0.27,"output":1.08,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.4725,"blendedTrusted":null,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-27","lastUpdated":"2026-03-27","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-pro/"},{"id":"minimax/minimax-m3-eu","name":"MiniMax-M3 (EU)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":1048576,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"requesty","input":0.36,"output":1.8,"cacheRead":0.09,"official":false},"cheapest":{"provider":"requesty","input":0.36,"output":1.8,"cacheRead":0.09},"blendedRef":0.72,"blendedMin":0.72,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/minimax/minimax-m3-eu/"},{"id":"openai/gpt-4.1-eu","name":"GPT-4.1 (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":1.98,"output":7.92,"cacheRead":0.495,"official":false},"cheapest":{"provider":"requesty","input":1.98,"output":7.92,"cacheRead":0.495},"blendedRef":3.465,"blendedMin":3.465,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-eu/"},{"id":"nvidia/nemotron-3-nano-omni-eu","name":"nemotron-3-nano-omni@eu","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":300000,"contextRange":null,"outputLimit":300000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.054,"output":0.216,"cacheRead":0.054,"official":false},"cheapest":{"provider":"requesty","input":0.054,"output":0.216,"cacheRead":0.054},"blendedRef":0.0945,"blendedMin":0.0945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-20","lastUpdated":"2026-05-20","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni-eu/"},{"id":"deepseek/deepseek-v4-flash-0731-eu","name":"DeepSeek V4 Flash 0731 (EU)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.126,"output":0.252,"cacheRead":0.063,"official":false},"cheapest":{"provider":"requesty","input":0.126,"output":0.252,"cacheRead":0.063},"blendedRef":0.1575,"blendedMin":0.1575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-31","lastUpdated":"2026-07-31","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-0731-eu/"},{"id":"anthropic/claude-haiku-4-5-eu","name":"Claude Haiku 4.5 (latest) (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":0.99,"output":4.95,"cacheRead":0.099,"official":false},"cheapest":{"provider":"requesty","input":0.99,"output":4.95,"cacheRead":0.099},"blendedRef":1.98,"blendedMin":1.98,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-10-15","url":"https://llmpricing.dev/m/anthropic/claude-haiku-4-5-eu/"},{"id":"misc/ling-3.0-tiny","name":"ling-3.0-tiny","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":{"idx":24.5,"coding":26.5,"agentic":16,"speed":158,"ttft":2.59,"taskCost":0},"usage":null,"releaseDate":"2026-08-05","lastUpdated":"2026-08-05","url":"https://llmpricing.dev/m/misc/ling-3.0-tiny/"},{"id":"mistral/devstral-latest-eu","name":"devstral-latest@eu","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396,"official":false},"cheapest":{"provider":"requesty","input":0.396,"output":1.98,"cacheRead":0.396},"blendedRef":0.792,"blendedMin":0.792,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-27","lastUpdated":"2026-05-27","url":"https://llmpricing.dev/m/mistral/devstral-latest-eu/"},{"id":"nvidia/nvidia-nemotron-3-ultra","name":"nvidia-nemotron-3-ultra","lab":"nvidia","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":[256000,262144],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.625,"output":3.125,"cacheRead":0.1875,"official":false},"cheapest":{"provider":"requesty","input":0.45,"output":2.25,"cacheRead":null},"blendedRef":1.25,"blendedMin":0.9,"blendedTrusted":null,"spread":1.4,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-06-23","lastUpdated":"2026-06-23","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-3-ultra/"},{"id":"openai/gpt-4o-mini-eu","name":"GPT-4o mini (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":0.1485,"output":0.594,"cacheRead":0.07425,"official":false},"cheapest":{"provider":"requesty","input":0.1485,"output":0.594,"cacheRead":0.07425},"blendedRef":0.2599,"blendedMin":0.2599,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-eu/"},{"id":"google/gemini-3.7-flash-eu","name":"Gemini 3.7 Flash (EU)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":1.5,"output":7.5,"cacheRead":0.15,"official":false},"cheapest":{"provider":"requesty","input":0.66,"output":3.3,"cacheRead":0.066},"blendedRef":3,"blendedMin":1.32,"blendedTrusted":null,"spread":2.3,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-08-13","lastUpdated":"2026-08-13","url":"https://llmpricing.dev/m/google/gemini-3.7-flash-eu/"},{"id":"openai/gpt-5.4-eu","name":"GPT-5.4 (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":2.25,"output":13.5,"cacheRead":0.225,"official":false},"cheapest":{"provider":"requesty","input":2.25,"output":13.5,"cacheRead":0.225},"blendedRef":5.0625,"blendedMin":5.0625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-eu/"},{"id":"anthropic/claude-sonnet-4-eu","name":"Claude Sonnet 4 (latest) (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":2.7,"output":13.5,"cacheRead":0.27,"official":false},"cheapest":{"provider":"requesty","input":2.7,"output":13.5,"cacheRead":0.27},"blendedRef":5.4,"blendedMin":5.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4-eu/"},{"id":"openai/gpt-5.6-terra-eu","name":"GPT-5.6 Terra (EU)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":1.98,"output":11.88,"cacheRead":0.198,"official":false},"cheapest":{"provider":"requesty","input":1.98,"output":11.88,"cacheRead":0.198},"blendedRef":4.455,"blendedMin":4.455,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra-eu/"},{"id":"alibaba/thinkingcap-qwen3.6-27b","name":"thinkingcap-qwen3.6-27b","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0.36,"output":2.7,"cacheRead":0.234,"official":false},"cheapest":{"provider":"requesty","input":0.36,"output":2.7,"cacheRead":0.234},"blendedRef":0.945,"blendedMin":0.945,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-13","lastUpdated":"2026-07-13","url":"https://llmpricing.dev/m/alibaba/thinkingcap-qwen3.6-27b/"},{"id":"google/gemini-3.5-flash-lite-eu","name":"Gemini 3.5 Flash Lite (EU)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"requesty","input":0.297,"output":2.475,"cacheRead":0.0297},"blendedRef":0.85,"blendedMin":0.8415,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-lite-eu/"},{"id":"misc/leanstral-1-5","name":"leanstral-1-5","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-27","lastUpdated":"2026-05-27","url":"https://llmpricing.dev/m/misc/leanstral-1-5/"},{"id":"anthropic/claude-opus-4-5-eu","name":"Claude Opus 4.5 (latest) (EU)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"requesty","input":4.95,"output":24.75,"cacheRead":0.495,"official":false},"cheapest":{"provider":"requesty","input":4.95,"output":24.75,"cacheRead":0.495},"blendedRef":9.9,"blendedMin":9.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-24","lastUpdated":"2025-11-24","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-5-eu/"},{"id":"poolside/laguna-xs.2","name":"Laguna XS.2","lab":"poolside","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/poolside/laguna-xs.2/"},{"id":"zhipuai/glm-5.1-eu","name":"GLM-5.1 (EU)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":200000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"requesty","input":1.26,"output":3.96,"cacheRead":1.26,"official":false},"cheapest":{"provider":"requesty","input":1.26,"output":3.96,"cacheRead":1.26},"blendedRef":1.935,"blendedMin":1.935,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-eu/"},{"id":"mistral/mistral-medium-3-5-eu","name":"mistral-medium-3-5@eu","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"requesty","input":1.485,"output":7.425,"cacheRead":1.485,"official":false},"cheapest":{"provider":"requesty","input":1.485,"output":7.425,"cacheRead":1.485},"blendedRef":2.97,"blendedMin":2.97,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/mistral/mistral-medium-3-5-eu/"},{"id":"tencent/hunyuan-a13b-instruct-2","name":"tencent/Hunyuan-A13B-Instruct","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[131000,131072],"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.14,"output":0.57,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.14,"output":0.57,"cacheRead":null},"blendedRef":0.2475,"blendedMin":0.2475,"blendedTrusted":0.2475,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/tencent/hunyuan-a13b-instruct-2/"},{"id":"minimax/minimax-m2.5-6","name":"MiniMaxAI/MiniMax-M2.5","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":197000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow","input":0.3,"output":1.2,"cacheRead":0.03,"official":false},"cheapest":{"provider":"siliconflow","input":0.3,"output":1.2,"cacheRead":0.03},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":0.525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-15","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-6/"},{"id":"moonshotai/kimi-k2.6-12","name":"moonshotai/Kimi-K2.6","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"siliconflow","input":0.77,"output":4,"cacheRead":0.2,"official":false},"cheapest":{"provider":"siliconflow","input":0.77,"output":4,"cacheRead":0.2},"blendedRef":1.5775,"blendedMin":1.5775,"blendedTrusted":1.5775,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-12/"},{"id":"inclusionai/ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.14,"output":0.57,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.14,"output":0.57,"cacheRead":null},"blendedRef":0.2475,"blendedMin":0.2475,"blendedTrusted":0.2475,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":{"idx":9.6,"coding":null,"agentic":null,"speed":84,"ttft":2.25,"taskCost":null},"usage":null,"releaseDate":"2025-09-18","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/inclusionai/ling-flash-2.0/"},{"id":"deepseek/deepseek-v3.1-terminus-4","name":"deepseek-ai/DeepSeek-V3.1-Terminus","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.27,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.27,"output":1,"cacheRead":null},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":0.4525,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus-4/"},{"id":"deepseek/deepseek-r1-2","name":"deepseek-ai/DeepSeek-R1","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.5,"output":2.18,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.5,"output":2.18,"cacheRead":null},"blendedRef":0.92,"blendedMin":0.92,"blendedTrusted":0.92,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-05-28","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-2/"},{"id":"deepseek/deepseek-v3.2-8","name":"deepseek-ai/DeepSeek-V3.2","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.27,"output":0.42,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.27,"output":0.42,"cacheRead":null},"blendedRef":0.3075,"blendedMin":0.3075,"blendedTrusted":0.3075,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-03","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-8/"},{"id":"deepseek/deepseek-v3.1-2","name":"deepseek-ai/DeepSeek-V3.1","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow","input":0.27,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.27,"output":1,"cacheRead":null},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":0.4525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-25","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-2/"},{"id":"deepseek/deepseek-v3.2-exp-3","name":"deepseek-ai/DeepSeek-V3.2-Exp","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow","input":0.27,"output":0.41,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.27,"output":0.41,"cacheRead":null},"blendedRef":0.305,"blendedMin":0.305,"blendedTrusted":0.305,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-10","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-exp-3/"},{"id":"deepseek/deepseek-v3-2","name":"deepseek-ai/DeepSeek-V3","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.25,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.25,"output":1,"cacheRead":null},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-12-26","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3-2/"},{"id":"stepfun/step-3.5-flash-3","name":"stepfun-ai/Step-3.5-Flash","lab":"stepfun","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-02-11","lastUpdated":"2026-02-11","url":"https://llmpricing.dev/m/stepfun/step-3.5-flash-3/"},{"id":"alibaba/qwen3-vl-235b-a22b-thinking-3","name":"Qwen/Qwen3-VL-235B-A22B-Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0.45,"output":3.5,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.45,"output":3.5,"cacheRead":null},"blendedRef":1.2125,"blendedMin":1.2125,"blendedTrusted":1.2125,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-04","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-235b-a22b-thinking-3/"},{"id":"alibaba/qwen3-vl-30b-a3b-instruct-2","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":[131072,262000],"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.29,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.13,"output":0.52,"cacheRead":null},"blendedRef":0.4675,"blendedMin":0.2275,"blendedTrusted":0.4675,"spread":2.2,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-10-05","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-30b-a3b-instruct-2/"},{"id":"alibaba/qwen3.5-9b-3","name":"Qwen/Qwen3.5-9B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.22,"output":1.74,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.1,"output":0.15,"cacheRead":null},"blendedRef":0.6,"blendedMin":0.1125,"blendedTrusted":0.1125,"spread":2.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/alibaba/qwen3.5-9b-3/"},{"id":"alibaba/qwen3-14b-2","name":"Qwen/Qwen3-14B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":40960,"contextRange":[40960,131000],"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.2275,"output":0.91,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.07,"output":0.28,"cacheRead":null},"blendedRef":0.3981,"blendedMin":0.1225,"blendedTrusted":0.1225,"spread":3.3,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-30","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-14b-2/"},{"id":"alibaba/qwen3-32b-4","name":"Qwen/Qwen3-32B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.14,"output":0.57,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.14,"output":0.57,"cacheRead":null},"blendedRef":0.2475,"blendedMin":0.2475,"blendedTrusted":0.2475,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-04-30","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-32b-4/"},{"id":"alibaba/qwen3-vl-8b-instruct-2","name":"Qwen/Qwen3-VL-8B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":[131072,262000],"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.18,"output":0.68,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.08,"output":0.5,"cacheRead":null},"blendedRef":0.305,"blendedMin":0.185,"blendedTrusted":0.305,"spread":2.3,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-8b-instruct-2/"},{"id":"alibaba/qwen3-coder-30b-a3b-instruct-3","name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.07,"output":0.28,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.07,"output":0.28,"cacheRead":null},"blendedRef":0.1225,"blendedMin":0.1225,"blendedTrusted":0.1225,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-08-01","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-30b-a3b-instruct-3/"},{"id":"alibaba/qwen3-8b-2","name":"Qwen/Qwen3-8B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[131000,131072],"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.117,"output":0.455,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.06,"output":0.06,"cacheRead":null},"blendedRef":0.2015,"blendedMin":0.06,"blendedTrusted":0.06,"spread":2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-04-30","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-8b-2/"},{"id":"alibaba/qwen3-vl-30b-a3b-thinking-2","name":"Qwen/Qwen3-VL-30B-A3B-Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[131072,262000],"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":0.2,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.2,"output":1,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.4,"blendedTrusted":0.4675,"spread":1.4,"hostCount":4,"pricedHostCount":4,"aa":null,"usage":null,"releaseDate":"2025-10-11","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-30b-a3b-thinking-2/"},{"id":"alibaba/qwen3-30b-a3b-instruct-2507-2","name":"Qwen/Qwen3-30B-A3B-Instruct-2507","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":[128000,262000],"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.13,"output":0.52,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.09,"output":0.3,"cacheRead":null},"blendedRef":0.2275,"blendedMin":0.1425,"blendedTrusted":0.1425,"spread":1.4,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-07-30","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b-instruct-2507-2/"},{"id":"alibaba/qwen2.5-7b-instruct","name":"Qwen/Qwen2.5-7B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":[32768,33000],"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.05,"output":0.05,"cacheRead":null},"blendedRef":0.125,"blendedMin":0.05,"blendedTrusted":0.05,"spread":2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2024-09-18","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen2.5-7b-instruct/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507-5","name":"Qwen/Qwen3-235B-A22B-Thinking-2507","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":[131072,262000],"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.23,"output":2.3,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.13,"output":0.6,"cacheRead":null},"blendedRef":0.7475,"blendedMin":0.2475,"blendedTrusted":0.2475,"spread":1.8,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507-5/"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct-4","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.25,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.25,"output":1,"cacheRead":null},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-31","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-480b-a35b-instruct-4/"},{"id":"alibaba/qwen2.5-72b-instruct","name":"Qwen/Qwen2.5-72B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":33000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.59,"output":0.59,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.59,"output":0.59,"cacheRead":null},"blendedRef":0.59,"blendedMin":0.59,"blendedTrusted":0.59,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-09-18","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen2.5-72b-instruct/"},{"id":"alibaba/qwen3-vl-32b-instruct-2","name":"Qwen/Qwen3-VL-32B-Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":[131072,262000],"outputLimit":262000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0.2,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.104,"output":0.416,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.182,"blendedTrusted":0.3,"spread":1.9,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-10-21","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-32b-instruct-2/"},{"id":"alibaba/qwen3-vl-32b-thinking","name":"Qwen/Qwen3-VL-32B-Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0.2,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.2,"output":1.5,"cacheRead":null},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":0.525,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-10-21","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-32b-thinking/"},{"id":"zhipuai/glm-5v-turbo-2","name":"zai-org/GLM-5V-Turbo","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow","input":1.2,"output":4,"cacheRead":0.24,"official":false},"cheapest":{"provider":"siliconflow","input":1.2,"output":4,"cacheRead":0.24},"blendedRef":1.9,"blendedMin":1.9,"blendedTrusted":1.9,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-04-01","url":"https://llmpricing.dev/m/zhipuai/glm-5v-turbo-2/"},{"id":"zhipuai/glm-4.5-air-4","name":"zai-org/GLM-4.5-Air","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.14,"output":0.86,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.14,"output":0.86,"cacheRead":null},"blendedRef":0.32,"blendedMin":0.32,"blendedTrusted":0.32,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-28","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/zhipuai/glm-4.5-air-4/"},{"id":"zhipuai/glm-5.1-9","name":"zai-org/GLM-5.1","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":205000,"contextRange":null,"outputLimit":205000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"siliconflow","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":2.15,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-08","lastUpdated":"2026-04-08","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-9/"},{"id":"zhipuai/glm-5-9","name":"zai-org/GLM-5","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":205000,"contextRange":null,"outputLimit":205000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow","input":0.95,"output":2.55,"cacheRead":0.2,"official":false},"cheapest":{"provider":"siliconflow","input":0.95,"output":2.55,"cacheRead":0.2},"blendedRef":1.35,"blendedMin":1.35,"blendedTrusted":1.35,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/zhipuai/glm-5-9/"},{"id":"baidu/ernie-4.5-300b-a47b","name":"baidu/ERNIE-4.5-300B-A47B","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.28,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow","input":0.28,"output":1.1,"cacheRead":null},"blendedRef":0.485,"blendedMin":0.485,"blendedTrusted":0.485,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2025-07-02","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/baidu/ernie-4.5-300b-a47b/"},{"id":"meta/meta-llama-3-1-8b-instruct-gguf","name":"Meta Llama 3.1 8B Instruct (GGUF)","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"atomic-chat","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/meta-llama-3-1-8b-instruct-gguf/"},{"id":"alibaba/qwen3-5-9b-q4-k-m","name":"Qwen 3.5 9B (Q4_K_M)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"atomic-chat","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-04-04","url":"https://llmpricing.dev/m/alibaba/qwen3-5-9b-q4-k-m/"},{"id":"google/gemma-4-e4b-it-iq4-xs","name":"Gemma 4 E4B Instruct (IQ4_XS)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"atomic-chat","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-e4b-it-iq4-xs/"},{"id":"google/gemma-4-e4b-it-mlx-4bit","name":"Gemma 4 E4B Instruct (MLX 4-bit)","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"atomic-chat","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-e4b-it-mlx-4bit/"},{"id":"alibaba/qwen3-5-9b-mlx-4bit","name":"Qwen 3.5 9B (MLX 4-bit)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"atomic-chat","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-04-04","url":"https://llmpricing.dev/m/alibaba/qwen3-5-9b-mlx-4bit/"},{"id":"subconscious/tim-qwen3.6-27b","name":"TIM-Qwen3.6 27B","lab":"subconscious","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":5000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"subconscious","input":0.3,"output":3,"cacheRead":0.15,"official":true},"cheapest":{"provider":"subconscious","input":0.3,"output":3,"cacheRead":0.15},"blendedRef":0.975,"blendedMin":0.975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-11","lastUpdated":"2026-05-11","url":"https://llmpricing.dev/m/subconscious/tim-qwen3.6-27b/"},{"id":"misc/cheap","name":"Cheap","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-01","lastUpdated":"2026-06-27","url":"https://llmpricing.dev/m/misc/cheap/"},{"id":"misc/fast","name":"Fast","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-27","url":"https://llmpricing.dev/m/misc/fast/"},{"id":"misc/synth-code","name":"Synth Code","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-20","lastUpdated":"2026-06-27","url":"https://llmpricing.dev/m/misc/synth-code/"},{"id":"misc/e2e","name":"End-to-End Encrypted","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-27","url":"https://llmpricing.dev/m/misc/e2e/"},{"id":"misc/zdr","name":"Zero Data Retention","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-27","url":"https://llmpricing.dev/m/misc/zdr/"},{"id":"misc/synth","name":"Synth","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-20","lastUpdated":"2026-06-27","url":"https://llmpricing.dev/m/misc/synth/"},{"id":"zhipuai/zai-glm-5-1","name":"Z.AI GLM-5.1","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":198000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"frogbot","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"frogbot","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-20","lastUpdated":"2025-02-22","url":"https://llmpricing.dev/m/zhipuai/zai-glm-5-1/"},{"id":"nvidia/nemotron-120b-a12b","name":"Nemotron Super","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":202800,"contextRange":null,"outputLimit":202800,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"baseten","input":0.3,"output":0.75,"cacheRead":0.06,"official":false},"cheapest":{"provider":"baseten","input":0.3,"output":0.75,"cacheRead":0.06},"blendedRef":0.4125,"blendedMin":0.4125,"blendedTrusted":0.4125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-120b-a12b/"},{"id":"nvidia/nvidia-nemotron-3-ultra-550b-a55b","name":"Nemotron Ultra","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":202800,"contextRange":null,"outputLimit":202800,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"baseten","input":0.6,"output":2.4,"cacheRead":0.12,"official":false},"cheapest":{"provider":"baseten","input":0.6,"output":2.4,"cacheRead":0.12},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":1.05,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-3-ultra-550b-a55b/"},{"id":"openai/gpt-oss-120b-12","name":"OpenAI GPT 120B","lab":"openai","kind":"text","status":"ga","openWeights":true,"context":128072,"contextRange":null,"outputLimit":128072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"baseten","input":0.1,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"baseten","input":0.1,"output":0.5,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":0.2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-05","lastUpdated":"2025-08-05","url":"https://llmpricing.dev/m/openai/gpt-oss-120b-12/"},{"id":"paddlepaddle/paddleocr-vl-1.5","name":"PaddlePaddle/PaddleOCR-VL-1.5","lab":"paddlepaddle","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-29","lastUpdated":"2026-01-29","url":"https://llmpricing.dev/m/paddlepaddle/paddleocr-vl-1.5/"},{"id":"deepseek/deepseek-v4-pro-13","name":"deepseek-ai/DeepSeek-V4-Pro","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1049000,"contextRange":null,"outputLimit":393000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":1.74,"output":3.48,"cacheRead":0.145,"official":false},"cheapest":{"provider":"siliconflow-cn","input":1.74,"output":3.48,"cacheRead":0.145},"blendedRef":2.175,"blendedMin":2.175,"blendedTrusted":2.175,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-13/"},{"id":"deepseek/deepseek-ocr-3","name":"deepseek-ai/DeepSeek-OCR","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-20","lastUpdated":"2025-10-20","url":"https://llmpricing.dev/m/deepseek/deepseek-ocr-3/"},{"id":"minimax/minimax-m2.5-7","name":"Pro/MiniMaxAI/MiniMax-M2.5","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":192000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.3,"output":1.22,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.3,"output":1.22,"cacheRead":null},"blendedRef":0.53,"blendedMin":0.53,"blendedTrusted":0.53,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-13","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/minimax/minimax-m2.5-7/"},{"id":"moonshotai/kimi-k2.5-9","name":"Pro/moonshotai/Kimi-K2.5","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0.45,"output":2.25,"cacheRead":0.07,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.45,"output":2.25,"cacheRead":0.07},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":0.9,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-9/"},{"id":"moonshotai/kimi-k2.6-13","name":"Pro/moonshotai/Kimi-K2.6","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"siliconflow-cn","input":0.95,"output":4,"cacheRead":0.16,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.95,"output":4,"cacheRead":0.16},"blendedRef":1.7125,"blendedMin":1.7125,"blendedTrusted":1.7125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.6-13/"},{"id":"deepseek/deepseek-v3.1-terminus-5","name":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.27,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.27,"output":1,"cacheRead":null},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":0.4525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-29","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.1-terminus-5/"},{"id":"deepseek/deepseek-r1-3","name":"Pro/deepseek-ai/DeepSeek-R1","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.5,"output":2.18,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.5,"output":2.18,"cacheRead":null},"blendedRef":0.92,"blendedMin":0.92,"blendedTrusted":0.92,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-28","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-3/"},{"id":"deepseek/deepseek-v3.2-9","name":"Pro/deepseek-ai/DeepSeek-V3.2","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.27,"output":0.42,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.27,"output":0.42,"cacheRead":null},"blendedRef":0.3075,"blendedMin":0.3075,"blendedTrusted":0.3075,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-03","url":"https://llmpricing.dev/m/deepseek/deepseek-v3.2-9/"},{"id":"deepseek/deepseek-v3-3","name":"Pro/deepseek-ai/DeepSeek-V3","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":164000,"contextRange":null,"outputLimit":164000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":0.25,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.25,"output":1,"cacheRead":null},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-26","lastUpdated":"2025-11-25","url":"https://llmpricing.dev/m/deepseek/deepseek-v3-3/"},{"id":"zhipuai/glm-5.1-10","name":"Pro/zai-org/GLM-5.1","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":205000,"contextRange":null,"outputLimit":205000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"siliconflow-cn","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":2.15,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-08","lastUpdated":"2026-04-08","url":"https://llmpricing.dev/m/zhipuai/glm-5.1-10/"},{"id":"zhipuai/glm-5-10","name":"Pro/zai-org/GLM-5","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":205000,"contextRange":null,"outputLimit":205000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"siliconflow-cn","input":1,"output":3.2,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":1,"output":3.2,"cacheRead":null},"blendedRef":1.55,"blendedMin":1.55,"blendedTrusted":1.55,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-12","lastUpdated":"2026-02-12","url":"https://llmpricing.dev/m/zhipuai/glm-5-10/"},{"id":"alibaba/qwen3.5-4b-2","name":"Qwen/Qwen3.5-4B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/alibaba/qwen3.5-4b-2/"},{"id":"alibaba/qwen3.5-122b-a10b-3","name":"Qwen/Qwen3.5-122B-A10B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.29,"output":2.32,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.29,"output":2.32,"cacheRead":null},"blendedRef":0.7975,"blendedMin":0.7975,"blendedTrusted":0.7975,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-02-26","url":"https://llmpricing.dev/m/alibaba/qwen3.5-122b-a10b-3/"},{"id":"alibaba/qwen3.5-27b-3","name":"Qwen/Qwen3.5-27B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.26,"output":2.09,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.26,"output":2.09,"cacheRead":null},"blendedRef":0.7175,"blendedMin":0.7175,"blendedTrusted":0.7175,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-25","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/alibaba/qwen3.5-27b-3/"},{"id":"alibaba/qwen3.5-35b-a3b-2","name":"Qwen/Qwen3.5-35B-A3B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.23,"output":1.86,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.23,"output":1.86,"cacheRead":null},"blendedRef":0.6375,"blendedMin":0.6375,"blendedTrusted":0.6375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-25","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/alibaba/qwen3.5-35b-a3b-2/"},{"id":"alibaba/qwen3.5-397b-a17b-3","name":"Qwen/Qwen3.5-397B-A17B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.29,"output":1.74,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.29,"output":1.74,"cacheRead":null},"blendedRef":0.6525,"blendedMin":0.6525,"blendedTrusted":0.6525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-397b-a17b-3/"},{"id":"alibaba/qwen3.6-35b-a3b-5","name":"Qwen/Qwen3.6-35B-A3B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image","video"],"reference":{"provider":"siliconflow-cn","input":0.23,"output":1.86,"cacheRead":null,"official":false},"cheapest":{"provider":"siliconflow-cn","input":0.23,"output":1.86,"cacheRead":null},"blendedRef":0.6375,"blendedMin":0.6375,"blendedTrusted":0.6375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/alibaba/qwen3.6-35b-a3b-5/"},{"id":"trytako/tako","name":"Tako","lab":"trytako","kind":"text","status":"ga","openWeights":false,"context":2048,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-15","lastUpdated":"2024-08-15","url":"https://llmpricing.dev/m/trytako/tako/"},{"id":"elevenlabs/elevenlabs-v3","name":"ElevenLabs-v3","lab":"elevenlabs","kind":"audio","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-05","lastUpdated":"2025-06-05","url":"https://llmpricing.dev/m/elevenlabs/elevenlabs-v3/"},{"id":"elevenlabs/elevenlabs-v2.5-turbo","name":"ElevenLabs-v2.5-Turbo","lab":"elevenlabs","kind":"audio","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-28","lastUpdated":"2024-10-28","url":"https://llmpricing.dev/m/elevenlabs/elevenlabs-v2.5-turbo/"},{"id":"elevenlabs/elevenlabs-music","name":"ElevenLabs-Music","lab":"elevenlabs","kind":"audio","status":"ga","openWeights":false,"context":2000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-29","lastUpdated":"2025-08-29","url":"https://llmpricing.dev/m/elevenlabs/elevenlabs-music/"},{"id":"runwayml/runway","name":"Runway","lab":"runwayml","kind":"video","status":"ga","openWeights":false,"context":256,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-11","lastUpdated":"2024-10-11","url":"https://llmpricing.dev/m/runwayml/runway/"},{"id":"runwayml/runway-gen-4-turbo","name":"Runway-Gen-4-Turbo","lab":"runwayml","kind":"video","status":"ga","openWeights":false,"context":256,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-09","lastUpdated":"2025-05-09","url":"https://llmpricing.dev/m/runwayml/runway-gen-4-turbo/"},{"id":"ideogramai/ideogram","name":"Ideogram","lab":"ideogramai","kind":"image","status":"ga","openWeights":false,"context":150,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-04-03","lastUpdated":"2024-04-03","url":"https://llmpricing.dev/m/ideogramai/ideogram/"},{"id":"ideogramai/ideogram-v2","name":"Ideogram-v2","lab":"ideogramai","kind":"image","status":"ga","openWeights":false,"context":150,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-21","lastUpdated":"2024-08-21","url":"https://llmpricing.dev/m/ideogramai/ideogram-v2/"},{"id":"ideogramai/ideogram-v2a-turbo","name":"Ideogram-v2a-Turbo","lab":"ideogramai","kind":"image","status":"ga","openWeights":false,"context":150,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-02-27","lastUpdated":"2025-02-27","url":"https://llmpricing.dev/m/ideogramai/ideogram-v2a-turbo/"},{"id":"ideogramai/ideogram-v2a","name":"Ideogram-v2a","lab":"ideogramai","kind":"image","status":"ga","openWeights":false,"context":150,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-02-27","lastUpdated":"2025-02-27","url":"https://llmpricing.dev/m/ideogramai/ideogram-v2a/"},{"id":"google/imagen-4","name":"Imagen-4","lab":"google","kind":"image","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/google/imagen-4/"},{"id":"google/veo-2","name":"Veo-2","lab":"google","kind":"video","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-12-02","lastUpdated":"2024-12-02","url":"https://llmpricing.dev/m/google/veo-2/"},{"id":"google/gemini-3.1-pro","name":"Gemini-3.1-Pro","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"poe","input":2,"output":12,"cacheRead":0.2,"official":false},"cheapest":{"provider":"poe","input":2,"output":12,"cacheRead":0.2},"blendedRef":4.5,"blendedMin":4.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-19","lastUpdated":"2026-02-19","url":"https://llmpricing.dev/m/google/gemini-3.1-pro/"},{"id":"google/veo-3","name":"Veo-3","lab":"google","kind":"video","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-21","lastUpdated":"2025-05-21","url":"https://llmpricing.dev/m/google/veo-3/"},{"id":"google/gemini-deep-research","name":"gemini-deep-research","lab":"google","kind":"text","status":"deprecated","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"poe","input":1.6,"output":9.6,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":1.6,"output":9.6,"cacheRead":null},"blendedRef":3.6,"blendedMin":3.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/google/gemini-deep-research/"},{"id":"google/imagen-3","name":"Imagen-3","lab":"google","kind":"image","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-15","lastUpdated":"2024-10-15","url":"https://llmpricing.dev/m/google/imagen-3/"},{"id":"google/imagen-3-fast","name":"Imagen-3-Fast","lab":"google","kind":"image","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-17","lastUpdated":"2024-10-17","url":"https://llmpricing.dev/m/google/imagen-3-fast/"},{"id":"google/lyria","name":"Lyria","lab":"google","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-04","lastUpdated":"2025-06-04","url":"https://llmpricing.dev/m/google/lyria/"},{"id":"google/veo-3-fast","name":"Veo-3-Fast","lab":"google","kind":"video","status":"ga","openWeights":false,"context":480,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-13","lastUpdated":"2025-10-13","url":"https://llmpricing.dev/m/google/veo-3-fast/"},{"id":"novita/glm-4.7-n","name":"glm-4.7-n","lab":"novita","kind":"text","status":"ga","openWeights":false,"context":205000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-22","lastUpdated":"2025-12-22","url":"https://llmpricing.dev/m/novita/glm-4.7-n/"},{"id":"anthropic/claude-3-7-sonnet-20250219","name":"Claude Sonnet 3.7","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[196608,1000000],"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":2.6,"output":13,"cacheRead":0.26},"blendedRef":6,"blendedMin":5.2,"blendedTrusted":null,"spread":1.2,"hostCount":3,"pricedHostCount":3,"aa":null,"usage":null,"releaseDate":"2025-02-19","lastUpdated":"2025-02-19","url":"https://llmpricing.dev/m/anthropic/claude-3-7-sonnet-20250219/"},{"id":"anthropic/claude-3-haiku-20240307","name":"Claude Haiku 3","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":[189096,200000],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.25,"output":1.25,"cacheRead":0.03,"official":false},"cheapest":{"provider":"poe","input":0.21,"output":1.1,"cacheRead":0.021},"blendedRef":0.5,"blendedMin":0.4325,"blendedTrusted":0.5,"spread":1.2,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-03-13","lastUpdated":"2024-03-13","url":"https://llmpricing.dev/m/anthropic/claude-3-haiku-20240307/"},{"id":"anthropic/claude-sonnet-3.5","name":"Claude-Sonnet-3.5","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":189096,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"poe","input":2.6,"output":13,"cacheRead":0.26,"official":false},"cheapest":{"provider":"poe","input":2.6,"output":13,"cacheRead":0.26},"blendedRef":5.2,"blendedMin":5.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-05","lastUpdated":"2024-06-05","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-3.5/"},{"id":"anthropic/claude-sonnet-3.5-june","name":"Claude-Sonnet-3.5-June","lab":"anthropic","kind":"text","status":"deprecated","openWeights":false,"context":189096,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"poe","input":2.6,"output":13,"cacheRead":0.26,"official":false},"cheapest":{"provider":"poe","input":2.6,"output":13,"cacheRead":0.26},"blendedRef":5.2,"blendedMin":5.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-18","lastUpdated":"2024-11-18","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-3.5-june/"},{"id":"openai/gpt-3.5-turbo-raw","name":"GPT-3.5-Turbo-Raw","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":4524,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":0.45,"output":1.4,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.45,"output":1.4,"cacheRead":null},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-09-27","lastUpdated":"2023-09-27","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-raw/"},{"id":"openai/gpt-5.2-instant","name":"GPT-5.2-Instant","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":1.6,"output":13,"cacheRead":0.16,"official":false},"cheapest":{"provider":"poe","input":1.6,"output":13,"cacheRead":0.16},"blendedRef":4.45,"blendedMin":4.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-instant/"},{"id":"openai/o3-deep-research-2","name":"o3-deep-research","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":10,"output":40,"cacheRead":2.5,"official":false},"cheapest":{"provider":"poe","input":9,"output":36,"cacheRead":2.2},"blendedRef":17.5,"blendedMin":15.75,"blendedTrusted":17.5,"spread":1.1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-06-26","lastUpdated":"2024-06-26","url":"https://llmpricing.dev/m/openai/o3-deep-research-2/"},{"id":"openai/gpt-5-chat","name":"GPT-5-Chat","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":1.1,"output":9,"cacheRead":0.11,"official":false},"cheapest":{"provider":"poe","input":1.1,"output":9,"cacheRead":0.11},"blendedRef":3.075,"blendedMin":3.075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-chat/"},{"id":"openai/gpt-4-classic","name":"GPT-4-Classic","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":27,"output":54,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":27,"output":54,"cacheRead":null},"blendedRef":33.75,"blendedMin":33.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-03-25","lastUpdated":"2024-03-25","url":"https://llmpricing.dev/m/openai/gpt-4-classic/"},{"id":"openai/sora-2-pro","name":"Sora-2-Pro","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-06","lastUpdated":"2025-10-06","url":"https://llmpricing.dev/m/openai/sora-2-pro/"},{"id":"openai/gpt-4o-search","name":"GPT-4o-Search","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":2.2,"output":9,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":2.2,"output":9,"cacheRead":null},"blendedRef":3.9,"blendedMin":3.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-11","lastUpdated":"2025-03-11","url":"https://llmpricing.dev/m/openai/gpt-4o-search/"},{"id":"openai/o4-mini-deep-research-2","name":"o4-mini-deep-research","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":1.8,"output":7.2,"cacheRead":0.45,"official":false},"cheapest":{"provider":"poe","input":1.8,"output":7.2,"cacheRead":0.45},"blendedRef":3.15,"blendedMin":3.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-26","lastUpdated":"2024-06-26","url":"https://llmpricing.dev/m/openai/o4-mini-deep-research-2/"},{"id":"openai/dall-e-3","name":"DALL-E-3","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":800,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/dall-e-3/"},{"id":"openai/gpt-4-classic-0314","name":"GPT-4-Classic-0314","lab":"openai","kind":"text","status":"deprecated","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":27,"output":54,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":27,"output":54,"cacheRead":null},"blendedRef":33.75,"blendedMin":33.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-26","lastUpdated":"2024-08-26","url":"https://llmpricing.dev/m/openai/gpt-4-classic-0314/"},{"id":"openai/gpt-4o-mini-search","name":"GPT-4o-mini-Search","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":0.14,"output":0.54,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.14,"output":0.54,"cacheRead":null},"blendedRef":0.24,"blendedMin":0.24,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-11","lastUpdated":"2025-03-11","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-search/"},{"id":"openai/gpt-5.3-instant","name":"GPT-5.3-Instant","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":1.6,"output":13,"cacheRead":0.16,"official":false},"cheapest":{"provider":"poe","input":1.6,"output":13,"cacheRead":0.16},"blendedRef":4.45,"blendedMin":4.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-03","lastUpdated":"2026-03-03","url":"https://llmpricing.dev/m/openai/gpt-5.3-instant/"},{"id":"openai/gpt-4o-aug","name":"GPT-4o-Aug","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":2.2,"output":9,"cacheRead":1.1,"official":false},"cheapest":{"provider":"poe","input":2.2,"output":9,"cacheRead":1.1},"blendedRef":3.9,"blendedMin":3.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-21","lastUpdated":"2024-11-21","url":"https://llmpricing.dev/m/openai/gpt-4o-aug/"},{"id":"openai/sora-2","name":"Sora-2","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-06","lastUpdated":"2025-10-06","url":"https://llmpricing.dev/m/openai/sora-2/"},{"id":"openai/gpt-5.1-instant","name":"GPT-5.1-Instant","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":1.1,"output":9,"cacheRead":0.11,"official":false},"cheapest":{"provider":"poe","input":1.1,"output":9,"cacheRead":0.11},"blendedRef":3.075,"blendedMin":3.075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-12","lastUpdated":"2025-11-12","url":"https://llmpricing.dev/m/openai/gpt-5.1-instant/"},{"id":"xai/grok-3-2","name":"Grok 3","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":3,"output":15,"cacheRead":0.75,"official":false},"cheapest":{"provider":"poe","input":3,"output":15,"cacheRead":0.75},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":18.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-04-11","lastUpdated":"2025-04-11","url":"https://llmpricing.dev/m/xai/grok-3-2/"},{"id":"xai/grok-3-mini-2","name":"Grok 3 Mini","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":0.3,"output":0.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"poe","input":0.3,"output":0.5,"cacheRead":0.075},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-11","lastUpdated":"2025-04-11","url":"https://llmpricing.dev/m/xai/grok-3-mini-2/"},{"id":"lumalabs/ray2","name":"Ray2","lab":"lumalabs","kind":"video","status":"ga","openWeights":false,"context":5000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-02-20","lastUpdated":"2025-02-20","url":"https://llmpricing.dev/m/lumalabs/ray2/"},{"id":"poetools/claude-code","name":"claude-code","lab":"poetools","kind":"text","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-27","lastUpdated":"2025-11-27","url":"https://llmpricing.dev/m/poetools/claude-code/"},{"id":"stabilityai/stablediffusionxl","name":"StableDiffusionXL","lab":"stabilityai","kind":"image","status":"ga","openWeights":false,"context":200,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-07-09","lastUpdated":"2023-07-09","url":"https://llmpricing.dev/m/stabilityai/stablediffusionxl/"},{"id":"empiriolabs/deepseek-v4-flash-el","name":"DeepSeek-V4-Flash-EL","lab":"empiriolabs","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":0.14,"output":0.28,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.14,"output":0.28,"cacheRead":null},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-05-02","url":"https://llmpricing.dev/m/empiriolabs/deepseek-v4-flash-el/"},{"id":"empiriolabs/deepseek-v4-pro-el","name":"DeepSeek-V4-Pro-EL","lab":"empiriolabs","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":384000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":1.67,"output":3.33,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":1.67,"output":3.33,"cacheRead":null},"blendedRef":2.085,"blendedMin":2.085,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-05-02","url":"https://llmpricing.dev/m/empiriolabs/deepseek-v4-pro-el/"},{"id":"cerebras/qwen3-32b-cs","name":"qwen3-32b-cs","lab":"cerebras","kind":"text","status":"deprecated","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-15","lastUpdated":"2025-05-15","url":"https://llmpricing.dev/m/cerebras/qwen3-32b-cs/"},{"id":"cerebras/gpt-oss-120b-cs","name":"GPT-OSS-120B-CS","lab":"cerebras","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":0.35,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.35,"output":0.75,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-06","lastUpdated":"2025-08-06","url":"https://llmpricing.dev/m/cerebras/gpt-oss-120b-cs/"},{"id":"cerebras/llama-3.1-8b-cs","name":"Llama-3.1-8B-CS","lab":"cerebras","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":{"provider":"poe","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"poe","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-13","lastUpdated":"2025-05-13","url":"https://llmpricing.dev/m/cerebras/llama-3.1-8b-cs/"},{"id":"cerebras/qwen3-235b-2507-cs","name":"qwen3-235b-2507-cs","lab":"cerebras","kind":"text","status":"deprecated","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-06","lastUpdated":"2025-08-06","url":"https://llmpricing.dev/m/cerebras/qwen3-235b-2507-cs/"},{"id":"cerebras/llama-3.3-70b-cs","name":"llama-3.3-70b-cs","lab":"cerebras","kind":"text","status":"deprecated","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-13","lastUpdated":"2025-05-13","url":"https://llmpricing.dev/m/cerebras/llama-3.3-70b-cs/"},{"id":"fireworks-ai/kimi-k2.5-fw","name":"Kimi-K2.5-FW","lab":"fireworks-ai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"poe","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/fireworks-ai/kimi-k2.5-fw/"},{"id":"topazlabs-co/topazlabs","name":"TopazLabs","lab":"topazlabs-co","kind":"image","status":"ga","openWeights":false,"context":204,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-12-03","lastUpdated":"2024-12-03","url":"https://llmpricing.dev/m/topazlabs-co/topazlabs/"},{"id":"mistral/open-mixtral-8x7b","name":"Mixtral 8x7B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.7,"output":0.7,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.7,"output":0.7,"cacheRead":null},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":0.7,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-12-11","lastUpdated":"2023-12-11","url":"https://llmpricing.dev/m/mistral/open-mixtral-8x7b/"},{"id":"mistral/labs-devstral-small-2512","name":"Devstral Small 2","lab":"mistral","kind":"text","status":"deprecated","openWeights":true,"context":256000,"contextRange":null,"outputLimit":256000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"mistral","input":0,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"vercel","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0,"blendedMin":0.15,"blendedTrusted":0.15,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":{"idx":17.7,"coding":29.3,"agentic":10.8,"speed":132,"ttft":2.25,"taskCost":0},"usage":null,"releaseDate":"2025-12-09","lastUpdated":"2025-12-09","url":"https://llmpricing.dev/m/mistral/labs-devstral-small-2512/"},{"id":"mistral/open-mistral-nemo","name":"Open Mistral Nemo","lab":"mistral","kind":"text","status":"deprecated","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.15,"output":0.15,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":0.15,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/open-mistral-nemo/"},{"id":"mistral/magistral-small-2506-2","name":"Magistral Small","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.5,"output":1.5,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.5,"output":1.5,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":0.75,"spread":1,"hostCount":3,"pricedHostCount":3,"aa":{"idx":10.6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-06-10","lastUpdated":"2025-06-10","url":"https://llmpricing.dev/m/mistral/magistral-small-2506-2/"},{"id":"mistral/voxtral-mini-latest","name":"Voxtral Mini (latest)","lab":"mistral","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-02-01","url":"https://llmpricing.dev/m/mistral/voxtral-mini-latest/"},{"id":"mistral/ministral-3b-latest","name":"Ministral 3B (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.04,"output":0.04,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.04,"output":0.04,"cacheRead":null},"blendedRef":0.04,"blendedMin":0.04,"blendedTrusted":0.04,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-04","url":"https://llmpricing.dev/m/mistral/ministral-3b-latest/"},{"id":"mistral/ministral-8b-latest","name":"Ministral 8B (latest)","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.1,"output":0.1,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":0.1,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10-04","url":"https://llmpricing.dev/m/mistral/ministral-8b-latest/"},{"id":"mistral/open-mistral-7b","name":"Mistral 7B","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":8000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.25,"output":0.25,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.25,"output":0.25,"cacheRead":null},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":0.25,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-09-27","lastUpdated":"2023-09-27","url":"https://llmpricing.dev/m/mistral/open-mistral-7b/"},{"id":"mistral/voxtral-mini-tts-latest","name":"Voxtral Mini TTS (latest)","lab":"mistral","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/mistral/voxtral-mini-tts-latest/"},{"id":"mistral/mistral-embed","name":"Mistral Embed","lab":"mistral","kind":"embedding","status":"ga","openWeights":false,"context":8000,"contextRange":[8000,8192],"outputLimit":3072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"mistral","input":0.1,"output":0,"cacheRead":null,"official":true},"cheapest":{"provider":"mistral","input":0.1,"output":0,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":0.075,"spread":null,"hostCount":2,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-12-11","lastUpdated":"2023-12-11","url":"https://llmpricing.dev/m/mistral/mistral-embed/"},{"id":"xiaomi/xiaomi-mimo-v2.5-pro","name":"Xiaomi MiMo-V2.5-Pro","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":1.1,"output":3.3,"cacheRead":0.22,"official":false},"cheapest":{"provider":"aihubmix","input":1.1,"output":3.3,"cacheRead":0.22},"blendedRef":1.65,"blendedMin":1.65,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-05-13","url":"https://llmpricing.dev/m/xiaomi/xiaomi-mimo-v2.5-pro/"},{"id":"zhipuai/coding-glm-5.1","name":"Coding GLM 5.1","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.06,"output":0.22,"cacheRead":0.013,"official":false},"cheapest":{"provider":"aihubmix","input":0.06,"output":0.22,"cacheRead":0.013},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-11","lastUpdated":"2026-04-11","url":"https://llmpricing.dev/m/zhipuai/coding-glm-5.1/"},{"id":"zhipuai/glm-5v-turbo-3","name":"GLM 5 Vision Turbo","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"aihubmix","input":0.7042,"output":3.09848,"cacheRead":0.169008,"official":false},"cheapest":{"provider":"aihubmix","input":0.7042,"output":3.09848,"cacheRead":0.169008},"blendedRef":1.3028,"blendedMin":1.3028,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-09","lastUpdated":"2026-05-09","url":"https://llmpricing.dev/m/zhipuai/glm-5v-turbo-3/"},{"id":"xiaomi/xiaomi-mimo-v2.5-pro-free","name":"Xiaomi MiMo-V2.5-Pro (free)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-05-13","url":"https://llmpricing.dev/m/xiaomi/xiaomi-mimo-v2.5-pro-free/"},{"id":"xiaomi/coding-xiaomi-mimo-v2.5-pro","name":"Coding Xiaomi MiMo-V2.5-Pro","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.2,"output":0.6,"cacheRead":0.04,"official":false},"cheapest":{"provider":"aihubmix","input":0.2,"output":0.6,"cacheRead":0.04},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-05-13","url":"https://llmpricing.dev/m/xiaomi/coding-xiaomi-mimo-v2.5-pro/"},{"id":"misc/doubao-seed-2-0-lite-260428","name":"Doubao Seed 2.0 Lite 260428","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"aihubmix","input":0.08,"output":0.51,"cacheRead":0.01692,"official":false},"cheapest":{"provider":"aihubmix","input":0.08,"output":0.51,"cacheRead":0.01692},"blendedRef":0.1875,"blendedMin":0.1875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-28","url":"https://llmpricing.dev/m/misc/doubao-seed-2-0-lite-260428/"},{"id":"minimax/coding-minimax-m2.7-highspeed","name":"Coding MiniMax M2.7 Highspeed","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":128100,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"aihubmix","input":0.2,"output":0.2,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/coding-minimax-m2.7-highspeed/"},{"id":"zhipuai/coding-glm-5.1-free","name":"Coding GLM 5.1 (free)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-11","lastUpdated":"2026-04-11","url":"https://llmpricing.dev/m/zhipuai/coding-glm-5.1-free/"},{"id":"anthropic/claude-opus-4-7-think","name":"Claude Opus 4.7 Thinking","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"aihubmix","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"aihubmix","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/claude-opus-4-7-think/"},{"id":"misc/doubao-seed-2-0-mini-260428","name":"Doubao Seed 2.0 Mini 260428","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"aihubmix","input":0.03,"output":0.28,"cacheRead":0.00564,"official":false},"cheapest":{"provider":"aihubmix","input":0.03,"output":0.28,"cacheRead":0.00564},"blendedRef":0.0925,"blendedMin":0.0925,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-28","url":"https://llmpricing.dev/m/misc/doubao-seed-2-0-mini-260428/"},{"id":"minimax/coding-minimax-m2.7","name":"Coding MiniMax M2.7","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":128100,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.2,"output":0.2,"cacheRead":null,"official":false},"cheapest":{"provider":"aihubmix","input":0.2,"output":0.2,"cacheRead":null},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/coding-minimax-m2.7/"},{"id":"minimax/coding-minimax-m2.7-free","name":"Coding MiniMax M2.7 (Free)","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":204800,"contextRange":null,"outputLimit":128100,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-18","lastUpdated":"2026-03-18","url":"https://llmpricing.dev/m/minimax/coding-minimax-m2.7-free/"},{"id":"xiaomi/coding-xiaomi-mimo-v2.5","name":"Coding Xiaomi MiMo-V2.5","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"aihubmix","input":0.08,"output":0.4,"cacheRead":0.016,"official":false},"cheapest":{"provider":"aihubmix","input":0.08,"output":0.4,"cacheRead":0.016},"blendedRef":0.16,"blendedMin":0.16,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-05-13","url":"https://llmpricing.dev/m/xiaomi/coding-xiaomi-mimo-v2.5/"},{"id":"xiaomi/xiaomi-mimo-v2.5-free","name":"Xiaomi MiMo-V2.5 (free)","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"aihubmix","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-05-13","url":"https://llmpricing.dev/m/xiaomi/xiaomi-mimo-v2.5-free/"},{"id":"xiaomi/xiaomi-mimo-v2.5","name":"Xiaomi MiMo-V2.5","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","audio","video"],"reference":{"provider":"aihubmix","input":0.44,"output":2.2,"cacheRead":0.088,"official":false},"cheapest":{"provider":"aihubmix","input":0.44,"output":2.2,"cacheRead":0.088},"blendedRef":0.88,"blendedMin":0.88,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-05-13","url":"https://llmpricing.dev/m/xiaomi/xiaomi-mimo-v2.5/"},{"id":"zhipuai/alicloud-glm-5.1","name":"GLM-5.1 (Alibaba Cloud)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aihubmix","input":0.84,"output":3.38,"cacheRead":0.169,"official":false},"cheapest":{"provider":"aihubmix","input":0.84,"output":3.38,"cacheRead":0.169},"blendedRef":1.475,"blendedMin":1.475,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-27","lastUpdated":"2026-03-27","url":"https://llmpricing.dev/m/zhipuai/alicloud-glm-5.1/"},{"id":"misc/fugu-ultra-v1-0","name":"Fugu Ultra v1.0","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"empiriolabs","input":7.5,"output":45,"cacheRead":1.5,"official":false},"cheapest":{"provider":"empiriolabs","input":7.5,"output":45,"cacheRead":1.5},"blendedRef":16.875,"blendedMin":16.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-15","lastUpdated":"2026-06-15","url":"https://llmpricing.dev/m/misc/fugu-ultra-v1-0/"},{"id":"tencent/hunyuan-2.0-thinking","name":"Tencent HY 2.0 Think","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tencent-coding-plan","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-08","lastUpdated":"2026-03-08","url":"https://llmpricing.dev/m/tencent/hunyuan-2.0-thinking/"},{"id":"tencent/hunyuan-2.0-instruct","name":"Tencent HY 2.0 Instruct","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tencent-coding-plan","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-08","lastUpdated":"2026-03-08","url":"https://llmpricing.dev/m/tencent/hunyuan-2.0-instruct/"},{"id":"tencent/hunyuan-t1","name":"Hunyuan-T1","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tencent-coding-plan","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-08","lastUpdated":"2026-03-08","url":"https://llmpricing.dev/m/tencent/hunyuan-t1/"},{"id":"ibm/granite-4-h-small","name":"Granite-4.0-H-Small","lab":"ibm","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"watsonx","input":0.0636,"output":0.265,"cacheRead":null,"official":false},"cheapest":{"provider":"watsonx","input":0.0636,"output":0.265,"cacheRead":null},"blendedRef":0.114,"blendedMin":0.114,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":4.9,"coding":null,"agentic":null,"speed":25,"ttft":18.74,"taskCost":null},"usage":null,"releaseDate":"2025-10-02","lastUpdated":"2025-10-02","url":"https://llmpricing.dev/m/ibm/granite-4-h-small/"},{"id":"tencent/hy-mt2-plus","name":"Tencent Hy-MT2-Plus","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.074,"output":0.295,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.074,"output":0.295,"cacheRead":null},"blendedRef":0.1292,"blendedMin":0.1292,"blendedTrusted":0.1292,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/tencent/hy-mt2-plus/"},{"id":"tencent/hy-mt2-pro","name":"Tencent Hy-MT2-Pro","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.074,"output":0.295,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.074,"output":0.295,"cacheRead":null},"blendedRef":0.1292,"blendedMin":0.1292,"blendedTrusted":0.1292,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-21","lastUpdated":"2026-05-21","url":"https://llmpricing.dev/m/tencent/hy-mt2-pro/"},{"id":"tencent/hy-mt2-lite","name":"Tencent Hy-MT2-Lite","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.044,"output":0.177,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.044,"output":0.177,"cacheRead":null},"blendedRef":0.0773,"blendedMin":0.0773,"blendedTrusted":0.0773,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/tencent/hy-mt2-lite/"},{"id":"openai/s1-free","name":"S1 (Free)","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-20","lastUpdated":"2025-10-20","url":"https://llmpricing.dev/m/openai/s1-free/"},{"id":"openai/s2-pro-free","name":"S2 Pro (Free)","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/openai/s2-pro-free/"},{"id":"openai/s1","name":"S1","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-20","lastUpdated":"2025-10-20","url":"https://llmpricing.dev/m/openai/s1/"},{"id":"openai/transcribe-1","name":"Transcribe-1","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/openai/transcribe-1/"},{"id":"openai/transcribe-1-free","name":"Transcribe-1 (Free)","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-01","lastUpdated":"2026-03-01","url":"https://llmpricing.dev/m/openai/transcribe-1-free/"},{"id":"openai/s2-pro","name":"S2 Pro","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-09","lastUpdated":"2026-03-09","url":"https://llmpricing.dev/m/openai/s2-pro/"},{"id":"openai/s2.1-pro-free","name":"S2.1 Pro (Free)","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-28","lastUpdated":"2026-07-28","url":"https://llmpricing.dev/m/openai/s2.1-pro-free/"},{"id":"openai/s2.1-pro","name":"S2.1 Pro","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-28","lastUpdated":"2026-07-28","url":"https://llmpricing.dev/m/openai/s2.1-pro/"},{"id":"klingai/kling-v3.0-t2v","name":"Kling v3.0 Text-to-Video","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/klingai/kling-v3.0-t2v/"},{"id":"klingai/kling-v2.6-t2v","name":"Kling v2.6 Text-to-Video","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-21","url":"https://llmpricing.dev/m/klingai/kling-v2.6-t2v/"},{"id":"klingai/kling-v2.6-motion-control","name":"Kling v2.6 Motion Control","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-21","url":"https://llmpricing.dev/m/klingai/kling-v2.6-motion-control/"},{"id":"klingai/kling-v2.5-turbo-t2v","name":"Kling v2.5 Turbo Text-to-Video","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/klingai/kling-v2.5-turbo-t2v/"},{"id":"klingai/kling-v3.0-i2v","name":"Kling v3.0 Image-to-Video","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/klingai/kling-v3.0-i2v/"},{"id":"klingai/kling-v3.0-motion-control","name":"Kling v3.0 Motion Control","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-04","lastUpdated":"2026-03-04","url":"https://llmpricing.dev/m/klingai/kling-v3.0-motion-control/"},{"id":"klingai/kling-v2.6-i2v","name":"Kling v2.6 Image-to-Video","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-12-21","url":"https://llmpricing.dev/m/klingai/kling-v2.6-i2v/"},{"id":"klingai/kling-v2.5-turbo-i2v","name":"Kling v2.5 Turbo Image-to-Video","lab":"klingai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-23","url":"https://llmpricing.dev/m/klingai/kling-v2.5-turbo-i2v/"},{"id":"nvidia/nemotron-nano-12b-v2-vl-2","name":"Nvidia Nemotron Nano 12B V2 VL","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.2,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.2,"output":0.6,"cacheRead":null},"blendedRef":0.3,"blendedMin":0.3,"blendedTrusted":0.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":8.8,"coding":null,"agentic":null,"speed":101,"ttft":5.84,"taskCost":null},"usage":null,"releaseDate":"2025-10-28","lastUpdated":"2025-10-28","url":"https://llmpricing.dev/m/nvidia/nemotron-nano-12b-v2-vl-2/"},{"id":"nvidia/nemotron-3.5-lightning-3","name":"Nemotron 3.5 Lightning 30B","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.05,"output":0.2,"cacheRead":0.01,"official":false},"cheapest":{"provider":"vercel","input":0.05,"output":0.2,"cacheRead":0.01},"blendedRef":0.0875,"blendedMin":0.0875,"blendedTrusted":0.0875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-lightning-3/"},{"id":"google/veo-3.0-fast-generate-001","name":"Veo 3.0 Fast Generate","lab":"google","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-07-31","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/google/veo-3.0-fast-generate-001/"},{"id":"openai/text-embedding-005","name":"Text Embedding 005","lab":"openai","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-01","lastUpdated":"2024-08","url":"https://llmpricing.dev/m/openai/text-embedding-005/"},{"id":"google/gemini-3.1-flash-lite-image-2","name":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","lab":"google","kind":"image","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.25,"output":1.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"vercel","input":0.25,"output":1.5,"cacheRead":0.03},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":0.5625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-lite-image-2/"},{"id":"openai/text-multilingual-embedding-002","name":"Text Multilingual Embedding 002","lab":"openai","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-03-01","lastUpdated":"2024-03","url":"https://llmpricing.dev/m/openai/text-multilingual-embedding-002/"},{"id":"google/veo-3.0-generate-001","name":"Veo 3.0","lab":"google","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/google/veo-3.0-generate-001/"},{"id":"google/veo-3.1-lite-generate-001","name":"Veo 3.1 Lite Generate","lab":"google","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/veo-3.1-lite-generate-001/"},{"id":"google/gemini-3.1-flash-image-preview","name":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","lab":"google","kind":"image","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.5,"output":3,"cacheRead":0.05,"official":false},"cheapest":{"provider":"vercel","input":0.5,"output":3,"cacheRead":0.05},"blendedRef":1.125,"blendedMin":1.125,"blendedTrusted":1.125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-02-26","url":"https://llmpricing.dev/m/google/gemini-3.1-flash-image-preview/"},{"id":"google/veo-3.1-fast-generate-001","name":"Veo 3.1 Fast Generate","lab":"google","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-15","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/google/veo-3.1-fast-generate-001/"},{"id":"google/gemini-2.5-flash-image-3","name":"Nano Banana (Gemini 2.5 Flash Image)","lab":"google","kind":"image","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"vercel","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":0.85,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/google/gemini-2.5-flash-image-3/"},{"id":"bfl/flux-kontext-pro","name":"FLUX.1 Kontext Pro","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-29","lastUpdated":"2025-06","url":"https://llmpricing.dev/m/bfl/flux-kontext-pro/"},{"id":"bfl/flux-pro-1.1-ultra","name":"FLUX1.1 [pro] Ultra","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-11-01","lastUpdated":"2024-11","url":"https://llmpricing.dev/m/bfl/flux-pro-1.1-ultra/"},{"id":"bfl/flux-2-max","name":"FLUX.2 [max]","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":67300,"contextRange":null,"outputLimit":67300,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/bfl/flux-2-max/"},{"id":"bfl/flux-3-video","name":"Flux 3","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-04","lastUpdated":"2026-08-04","url":"https://llmpricing.dev/m/bfl/flux-3-video/"},{"id":"bfl/flux-pro-1.1","name":"FLUX1.1 [pro]","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-02","lastUpdated":"2024-10","url":"https://llmpricing.dev/m/bfl/flux-pro-1.1/"},{"id":"bfl/flux-pro-1.0-fill","name":"FLUX.1 Fill [pro]","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-01","lastUpdated":"2024-10","url":"https://llmpricing.dev/m/bfl/flux-pro-1.0-fill/"},{"id":"bfl/flux-2-klein-9b","name":"FLUX.2 [klein] 9B","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-15","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/bfl/flux-2-klein-9b/"},{"id":"bfl/flux-kontext-max","name":"FLUX.1 Kontext Max","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-29","lastUpdated":"2025-06","url":"https://llmpricing.dev/m/bfl/flux-kontext-max/"},{"id":"bfl/flux-2-pro","name":"FLUX.2 [pro]","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":67300,"contextRange":null,"outputLimit":67300,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-25","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/bfl/flux-2-pro/"},{"id":"bfl/flux-2-flex","name":"FLUX.2 [flex]","lab":"bfl","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-11-25","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/bfl/flux-2-flex/"},{"id":"inception/mercury-coder-small","name":"Mercury Coder Small Beta","lab":"inception","kind":"text","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.25,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.25,"output":1,"cacheRead":null},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-26","lastUpdated":"2025-02-26","url":"https://llmpricing.dev/m/inception/mercury-coder-small/"},{"id":"voyage/voyage-4-lite","name":"voyage-4-lite","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-15","lastUpdated":"2026-03-06","url":"https://llmpricing.dev/m/voyage/voyage-4-lite/"},{"id":"voyage/rerank-2.5","name":"Voyage Rerank 2.5","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-11","lastUpdated":"2025-08-11","url":"https://llmpricing.dev/m/voyage/rerank-2.5/"},{"id":"voyage/voyage-4","name":"voyage-4","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-15","lastUpdated":"2026-03-06","url":"https://llmpricing.dev/m/voyage/voyage-4/"},{"id":"voyage/voyage-law-2","name":"voyage-law-2","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-04-15","lastUpdated":"2024-03","url":"https://llmpricing.dev/m/voyage/voyage-law-2/"},{"id":"voyage/voyage-code-2","name":"voyage-code-2","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01","url":"https://llmpricing.dev/m/voyage/voyage-code-2/"},{"id":"voyage/voyage-3-large","name":"voyage-3-large","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-01-07","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/voyage/voyage-3-large/"},{"id":"voyage/voyage-3.5","name":"voyage-3.5","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/voyage/voyage-3.5/"},{"id":"voyage/voyage-finance-2","name":"voyage-finance-2","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-06-03","lastUpdated":"2024-03","url":"https://llmpricing.dev/m/voyage/voyage-finance-2/"},{"id":"voyage/voyage-3.5-lite","name":"voyage-3.5-lite","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/voyage/voyage-3.5-lite/"},{"id":"voyage/voyage-code-3","name":"voyage-code-3","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-12-04","lastUpdated":"2024-09","url":"https://llmpricing.dev/m/voyage/voyage-code-3/"},{"id":"voyage/voyage-4-large","name":"voyage-4-large","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-15","lastUpdated":"2026-03-06","url":"https://llmpricing.dev/m/voyage/voyage-4-large/"},{"id":"voyage/rerank-2.5-lite","name":"Voyage Rerank 2.5 Lite","lab":"voyage","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-08-11","lastUpdated":"2025-08-11","url":"https://llmpricing.dev/m/voyage/rerank-2.5-lite/"},{"id":"cohere/embed-v4.0","name":"Embed v4.0","lab":"cohere","kind":"embedding","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-04-15","lastUpdated":"2025-04-15","url":"https://llmpricing.dev/m/cohere/embed-v4.0/"},{"id":"openai/rerank-v3.5","name":"Cohere Rerank 3.5","lab":"openai","kind":"rerank","status":"ga","openWeights":false,"context":4096,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-12-02","lastUpdated":"2024-12-02","url":"https://llmpricing.dev/m/openai/rerank-v3.5/"},{"id":"openai/rerank-v4-pro","name":"Cohere Rerank 4 Pro","lab":"openai","kind":"rerank","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/rerank-v4-pro/"},{"id":"openai/rerank-v4-fast","name":"Cohere Rerank 4 Fast","lab":"openai","kind":"rerank","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/rerank-v4-fast/"},{"id":"bytedance/seedream-5.0-pro","name":"Seedream 5.0 Pro","lab":"bytedance","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-11","lastUpdated":"2026-07-11","url":"https://llmpricing.dev/m/bytedance/seedream-5.0-pro/"},{"id":"bytedance/seedance-2.5","name":"Seedance 2.5","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-07","lastUpdated":"2026-08-07","url":"https://llmpricing.dev/m/bytedance/seedance-2.5/"},{"id":"bytedance/seedance-v1.0-pro","name":"Seedance v1.0 Pro","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-06-11","lastUpdated":"2025-06-11","url":"https://llmpricing.dev/m/bytedance/seedance-v1.0-pro/"},{"id":"bytedance/seedance-2.0","name":"Seedance 2.0","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-14","lastUpdated":"2026-04-14","url":"https://llmpricing.dev/m/bytedance/seedance-2.0/"},{"id":"bytedance/seedream-4.0","name":"Seedream 4.0","lab":"bytedance","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-09","lastUpdated":"2025-08-28","url":"https://llmpricing.dev/m/bytedance/seedream-4.0/"},{"id":"bytedance/seedance-v1.0-pro-fast","name":"Seedance v1.0 Pro Fast","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-10-24","lastUpdated":"2025-10-31","url":"https://llmpricing.dev/m/bytedance/seedance-v1.0-pro-fast/"},{"id":"bytedance/seedream-5.0-lite","name":"Seedream 5.0 Lite","lab":"bytedance","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-13","lastUpdated":"2026-01-28","url":"https://llmpricing.dev/m/bytedance/seedream-5.0-lite/"},{"id":"bytedance/seedream-4.5","name":"Seedream 4.5","lab":"bytedance","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-03","lastUpdated":"2025-11-28","url":"https://llmpricing.dev/m/bytedance/seedream-4.5/"},{"id":"bytedance/seedance-v1.5-pro","name":"Seedance v1.5 Pro","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/bytedance/seedance-v1.5-pro/"},{"id":"bytedance/seedance-2.0-fast","name":"Seedance 2.0 Fast","lab":"bytedance","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-14","lastUpdated":"2026-04-14","url":"https://llmpricing.dev/m/bytedance/seedance-2.0-fast/"},{"id":"openai/gpt-4o-mini-fast","name":"GPT-4o mini (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.25,"output":1,"cacheRead":0.125,"official":false},"cheapest":{"provider":"vercel","input":0.25,"output":1,"cacheRead":0.125},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":0.4375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-fast/"},{"id":"openai/gpt-5.1-thinking","name":"GPT 5.1 Thinking","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"vercel","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":3.4375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-12","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5.1-thinking/"},{"id":"openai/gpt-5.1-thinking-fast","name":"GPT 5.1 Thinking (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":2.5,"output":20,"cacheRead":0.25,"official":false},"cheapest":{"provider":"vercel","input":2.5,"output":20,"cacheRead":0.25},"blendedRef":6.875,"blendedMin":6.875,"blendedTrusted":6.875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-12","lastUpdated":"2025-11-12","url":"https://llmpricing.dev/m/openai/gpt-5.1-thinking-fast/"},{"id":"openai/gpt-5.6-luna-fast","name":"GPT 5.6 Luna (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.4,"output":2.4,"cacheRead":0.04,"official":false},"cheapest":{"provider":"vercel","input":0.4,"output":2.4,"cacheRead":0.04},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":0.9,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-luna-fast/"},{"id":"openai/gpt-4o-mini-transcribe-2","name":"GPT-4o mini Transcribe","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":16000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["audio","text"],"reference":{"provider":"llmgateway","input":1.25,"output":5,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":1.25,"output":5,"cacheRead":null},"blendedRef":2.1875,"blendedMin":2.1875,"blendedTrusted":2.1875,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-03-13","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-transcribe-2/"},{"id":"openai/gpt-5.4-fast","name":"GPT 5.4 (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"vercel","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":11.25,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/gpt-5.4-fast/"},{"id":"openai/o4-mini-fast","name":"o4-mini (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":2,"output":8,"cacheRead":0.5,"official":false},"cheapest":{"provider":"vercel","input":2,"output":8,"cacheRead":0.5},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o4-mini-fast/"},{"id":"openai/gpt-5.5-fast","name":"GPT 5.5 (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":12.5,"output":75,"cacheRead":1.25,"official":false},"cheapest":{"provider":"vercel","input":12.5,"output":75,"cacheRead":1.25},"blendedRef":28.125,"blendedMin":28.125,"blendedTrusted":28.125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/gpt-5.5-fast/"},{"id":"openai/gpt-5.3-codex-fast","name":"GPT 5.3 Codex (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":3.5,"output":28,"cacheRead":0.35,"official":false},"cheapest":{"provider":"vercel","input":3.5,"output":28,"cacheRead":0.35},"blendedRef":9.625,"blendedMin":9.625,"blendedTrusted":9.625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/gpt-5.3-codex-fast/"},{"id":"openai/gpt-4o-transcribe-2","name":"GPT-4o Transcribe","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":16000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["audio","text"],"reference":{"provider":"llmgateway","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":4.375,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-03-13","lastUpdated":"2025-03-20","url":"https://llmpricing.dev/m/openai/gpt-4o-transcribe-2/"},{"id":"openai/gpt-4o-fast","name":"GPT-4o (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":4.25,"output":17,"cacheRead":2.125,"official":false},"cheapest":{"provider":"vercel","input":4.25,"output":17,"cacheRead":2.125},"blendedRef":7.4375,"blendedMin":7.4375,"blendedTrusted":7.4375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-05-13","lastUpdated":"2024-08-06","url":"https://llmpricing.dev/m/openai/gpt-4o-fast/"},{"id":"openai/gpt-5-fast","name":"GPT-5 (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":2.5,"output":20,"cacheRead":0.25,"official":false},"cheapest":{"provider":"vercel","input":2.5,"output":20,"cacheRead":0.25},"blendedRef":6.875,"blendedMin":6.875,"blendedTrusted":6.875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-fast/"},{"id":"openai/tts-1-hd","name":"TTS-1 HD","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/tts-1-hd/"},{"id":"openai/gpt-4.1-mini-fast","name":"GPT-4.1 mini (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.7,"output":2.8,"cacheRead":0.175,"official":false},"cheapest":{"provider":"vercel","input":0.7,"output":2.8,"cacheRead":0.175},"blendedRef":1.225,"blendedMin":1.225,"blendedTrusted":1.225,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-mini-fast/"},{"id":"openai/gpt-5.2-fast","name":"GPT 5.2 (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":3.5,"output":28,"cacheRead":0.35,"official":false},"cheapest":{"provider":"vercel","input":3.5,"output":28,"cacheRead":0.35},"blendedRef":9.625,"blendedMin":9.625,"blendedTrusted":9.625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-11","lastUpdated":"2025-12-11","url":"https://llmpricing.dev/m/openai/gpt-5.2-fast/"},{"id":"openai/tts-1","name":"TTS-1","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2023-11-06","lastUpdated":"2023-11-06","url":"https://llmpricing.dev/m/openai/tts-1/"},{"id":"openai/gpt-5-mini-fast","name":"GPT-5 mini (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.45,"output":3.6,"cacheRead":0.045,"official":false},"cheapest":{"provider":"vercel","input":0.45,"output":3.6,"cacheRead":0.045},"blendedRef":1.2375,"blendedMin":1.2375,"blendedTrusted":1.2375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-07","lastUpdated":"2025-08-07","url":"https://llmpricing.dev/m/openai/gpt-5-mini-fast/"},{"id":"openai/gpt-realtime-mini","name":"GPT-Realtime mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","audio"],"reference":{"provider":"vercel","input":0.6,"output":2.4,"cacheRead":0.06,"official":false},"cheapest":{"provider":"vercel","input":0.6,"output":2.4,"cacheRead":0.06},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":1.05,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-10","lastUpdated":"2025-10-10","url":"https://llmpricing.dev/m/openai/gpt-realtime-mini/"},{"id":"openai/gpt-5.6-sol-fast","name":"GPT 5.6 Sol (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"vercel","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":11.25,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-fast/"},{"id":"openai/gpt-5.4-mini-fast","name":"GPT 5.4 Mini (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":1.5,"output":9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"vercel","input":1.5,"output":9,"cacheRead":0.15},"blendedRef":3.375,"blendedMin":3.375,"blendedTrusted":3.375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/gpt-5.4-mini-fast/"},{"id":"openai/o3-fast","name":"o3 (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":100000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":3.5,"output":14,"cacheRead":0.875,"official":false},"cheapest":{"provider":"vercel","input":3.5,"output":14,"cacheRead":0.875},"blendedRef":6.125,"blendedMin":6.125,"blendedTrusted":6.125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-16","lastUpdated":"2025-04-16","url":"https://llmpricing.dev/m/openai/o3-fast/"},{"id":"openai/gpt-realtime-whisper","name":"GPT Realtime Whisper","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/openai/gpt-realtime-whisper/"},{"id":"openai/whisper-1","name":"Whisper","lab":"openai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":2,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2022-09-21","lastUpdated":"2025-09-05","url":"https://llmpricing.dev/m/openai/whisper-1/"},{"id":"openai/gpt-4.1-fast","name":"GPT-4.1 (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":3.5,"output":14,"cacheRead":0.875,"official":false},"cheapest":{"provider":"vercel","input":3.5,"output":14,"cacheRead":0.875},"blendedRef":6.125,"blendedMin":6.125,"blendedTrusted":6.125,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-fast/"},{"id":"openai/gpt-5.6-terra-fast","name":"GPT 5.6 Terra (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":4,"output":24,"cacheRead":0.4,"official":false},"cheapest":{"provider":"vercel","input":4,"output":24,"cacheRead":0.4},"blendedRef":9,"blendedMin":9,"blendedTrusted":9,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/gpt-5.6-terra-fast/"},{"id":"openai/gpt-realtime-2","name":"gpt-realtime-2","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","audio"],"reference":{"provider":"vercel","input":4,"output":24,"cacheRead":0.4,"official":false},"cheapest":{"provider":"vercel","input":4,"output":24,"cacheRead":0.4},"blendedRef":9,"blendedMin":9,"blendedTrusted":9,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-07","lastUpdated":"2026-05-07","url":"https://llmpricing.dev/m/openai/gpt-realtime-2/"},{"id":"openai/gpt-4.1-nano-fast","name":"GPT-4.1 nano (Fast)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1047576,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.2,"output":0.8,"cacheRead":0.05,"official":false},"cheapest":{"provider":"vercel","input":0.2,"output":0.8,"cacheRead":0.05},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":0.35,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/openai/gpt-4.1-nano-fast/"},{"id":"stepfun/step-3.5-flash-4","name":"StepFun 3.5 Flash","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":262114,"contextRange":null,"outputLimit":262114,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.09,"output":0.3,"cacheRead":0.02,"official":false},"cheapest":{"provider":"vercel","input":0.09,"output":0.3,"cacheRead":0.02},"blendedRef":0.1425,"blendedMin":0.1425,"blendedTrusted":0.1425,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-29","lastUpdated":"2026-02-13","url":"https://llmpricing.dev/m/stepfun/step-3.5-flash-4/"},{"id":"openai/arrow-1.1","name":"Arrow 1.1","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/openai/arrow-1.1/"},{"id":"xiaomi/mimo-v2.5-3","name":"MiMo M2.5","lab":"xiaomi","kind":"text","status":"ga","openWeights":true,"context":1050000,"contextRange":null,"outputLimit":131100,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.14,"output":0.28,"cacheRead":0.0028,"official":false},"cheapest":{"provider":"vercel","input":0.14,"output":0.28,"cacheRead":0.0028},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":0.175,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-22","lastUpdated":"2026-04-22","url":"https://llmpricing.dev/m/xiaomi/mimo-v2.5-3/"},{"id":"openai/wan-v2.5-t2v-preview","name":"Wan v2.5 Text-to-Video Preview","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-24","lastUpdated":"2025-09-24","url":"https://llmpricing.dev/m/openai/wan-v2.5-t2v-preview/"},{"id":"alibaba/qwen3-vl-instruct","name":"Qwen3 VL Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":129024,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"vercel","input":0.4,"output":1.6,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.4,"output":1.6,"cacheRead":null},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":0.7,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-24","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-instruct/"},{"id":"openai/wan-v2.7-r2v","name":"Wan v2.7 Reference-to-Video","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/openai/wan-v2.7-r2v/"},{"id":"openai/wan-v2.7-t2v","name":"Wan v2.7 Text-to-Video","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-07","lastUpdated":"2026-04-07","url":"https://llmpricing.dev/m/openai/wan-v2.7-t2v/"},{"id":"openai/wan-v2.6-i2v-flash","name":"Wan v2.6 Image-to-Video Flash","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/openai/wan-v2.6-i2v-flash/"},{"id":"openai/wan-v2.6-r2v-flash","name":"Wan v2.6 Reference-to-Video Flash","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/openai/wan-v2.6-r2v-flash/"},{"id":"alibaba/qwen3-vl-thinking","name":"Qwen3 VL Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":0.4,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":0.4,"output":4,"cacheRead":null},"blendedRef":1.3,"blendedMin":1.3,"blendedTrusted":1.3,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-23","lastUpdated":"2025-09-24","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-thinking/"},{"id":"openai/wan-v2.6-r2v","name":"Wan v2.6 Reference-to-Video","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/openai/wan-v2.6-r2v/"},{"id":"openai/wan-v2.6-t2v","name":"Wan v2.6 Text-to-Video","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/openai/wan-v2.6-t2v/"},{"id":"openai/wan-v2.6-i2v","name":"Wan v2.6 Image-to-Video","lab":"openai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/openai/wan-v2.6-i2v/"},{"id":"xai/grok-4.20-multi-agent-beta","name":"Grok 4.20 Multi Agent Beta","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"vercel","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":1.5625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/xai/grok-4.20-multi-agent-beta/"},{"id":"xai/grok-imagine-video-2","name":"Grok Imagine","lab":"xai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-28","lastUpdated":"2026-01-28","url":"https://llmpricing.dev/m/xai/grok-imagine-video-2/"},{"id":"xai/grok-4.20-reasoning-beta","name":"Grok 4.20 Beta Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"vercel","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":1.5625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/xai/grok-4.20-reasoning-beta/"},{"id":"xai/grok-4.20-non-reasoning-beta","name":"Grok 4.20 Beta Non-Reasoning","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":1.25,"output":2.5,"cacheRead":0.4,"official":false},"cheapest":{"provider":"vercel","input":1.25,"output":2.5,"cacheRead":0.4},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":1.5625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/xai/grok-4.20-non-reasoning-beta/"},{"id":"xai/grok-tts","name":"Grok TTS","lab":"xai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/xai/grok-tts/"},{"id":"xai/grok-voice-think-fast-1.0","name":"Grok Voice Think Fast 1.0","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/xai/grok-voice-think-fast-1.0/"},{"id":"xai/grok-imagine-video-1.5-preview","name":"Grok Imagine Video 1.5 Preview","lab":"xai","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-30","lastUpdated":"2026-05-30","url":"https://llmpricing.dev/m/xai/grok-imagine-video-1.5-preview/"},{"id":"xai/grok-stt","name":"Grok STT","lab":"xai","kind":"audio","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-16","lastUpdated":"2026-03-16","url":"https://llmpricing.dev/m/xai/grok-stt/"},{"id":"xai/grok-voice-think-fast-2.0","name":"Grok Voice Think Fast 2.0","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","audio"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-29","lastUpdated":"2026-07-29","url":"https://llmpricing.dev/m/xai/grok-voice-think-fast-2.0/"},{"id":"perplexity/pplx-embed-v1-4b","name":"Embed v1 4b","lab":"perplexity","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-26","lastUpdated":"2026-02-26","url":"https://llmpricing.dev/m/perplexity/pplx-embed-v1-4b/"},{"id":"perplexity/pplx-embed-v1-0.6b","name":"Embed v1 0.6b","lab":"perplexity","kind":"embedding","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":{"rank":49,"tokens":478788656653,"share":0.0017942879035602838},"releaseDate":"2026-02-26","lastUpdated":"2026-02-26","url":"https://llmpricing.dev/m/perplexity/pplx-embed-v1-0.6b/"},{"id":"recraft/recraft-v4.1","name":"Recraft V4.1","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-14","lastUpdated":"2026-05-14","url":"https://llmpricing.dev/m/recraft/recraft-v4.1/"},{"id":"recraft/recraft-v4.1-utility-pro","name":"Recraft V4.1 Utility Pro","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-14","lastUpdated":"2026-05-14","url":"https://llmpricing.dev/m/recraft/recraft-v4.1-utility-pro/"},{"id":"recraft/recraft-v2","name":"Recraft V2","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-03-13","lastUpdated":"2024-03","url":"https://llmpricing.dev/m/recraft/recraft-v2/"},{"id":"recraft/recraft-v4.1-pro","name":"Recraft V4.1 Pro","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-14","lastUpdated":"2026-05-14","url":"https://llmpricing.dev/m/recraft/recraft-v4.1-pro/"},{"id":"recraft/recraft-v4.1-utility","name":"Recraft V4.1 Utility","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-14","lastUpdated":"2026-05-14","url":"https://llmpricing.dev/m/recraft/recraft-v4.1-utility/"},{"id":"recraft/recraft-v3","name":"Recraft V3","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-10-30","lastUpdated":"2024-10","url":"https://llmpricing.dev/m/recraft/recraft-v3/"},{"id":"recraft/recraft-v4","name":"Recraft V4","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-02-17","url":"https://llmpricing.dev/m/recraft/recraft-v4/"},{"id":"recraft/recraft-v4-pro","name":"Recraft V4 Pro","lab":"recraft","kind":"image","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-02-17","url":"https://llmpricing.dev/m/recraft/recraft-v4-pro/"},{"id":"mistral/codestral-embed","name":"Codestral Embed","lab":"mistral","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-05-28","lastUpdated":"2025-05-28","url":"https://llmpricing.dev/m/mistral/codestral-embed/"},{"id":"amazon/titan-embed-text-v2","name":"Titan Text Embeddings V2","lab":"amazon","kind":"embedding","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":1536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-04-30","lastUpdated":"2024-04","url":"https://llmpricing.dev/m/amazon/titan-embed-text-v2/"},{"id":"prodia/flux-fast-schnell","name":"Flux Schnell","lab":"prodia","kind":"image","status":"ga","openWeights":false,"context":512,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-08-02","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/prodia/flux-fast-schnell/"},{"id":"interfaze/interfaze-beta","name":"Interfaze Beta","lab":"interfaze","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text","image","pdf"],"reference":{"provider":"vercel","input":1.5,"output":3.5,"cacheRead":null,"official":false},"cheapest":{"provider":"vercel","input":1.5,"output":3.5,"cacheRead":null},"blendedRef":2,"blendedMin":2,"blendedTrusted":2,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-07","lastUpdated":"2026-04-29","url":"https://llmpricing.dev/m/interfaze/interfaze-beta/"},{"id":"kwaipilot/kat-coder-pro-v1","name":"KAT-Coder-Pro V1","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vercel","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"vercel","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":0.525,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":28.9,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-11-09","lastUpdated":"2025-10-24","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-pro-v1/"},{"id":"minimax/minimax-h3","name":"MiniMax H3","lab":"minimax","kind":"video","status":"ga","openWeights":false,"context":0,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-30","lastUpdated":"2026-07-30","url":"https://llmpricing.dev/m/minimax/minimax-h3/"},{"id":"google/gemini-3.7-flash-us","name":"Gemini 3.7 Flash (US)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":1.5,"output":7.5,"cacheRead":0.15,"official":false},"cheapest":{"provider":"edenai","input":1.5,"output":7.5,"cacheRead":0.15},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-13","lastUpdated":"2026-08-13","url":"https://llmpricing.dev/m/google/gemini-3.7-flash-us/"},{"id":"google/gemini-3.6-flash-eu","name":"Gemini 3.6 Flash (EU)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"edenai","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.6-flash-eu/"},{"id":"google/gemini-3.5-flash-us","name":"Gemini 3.5 Flash (US)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":1.5,"output":9,"cacheRead":0.15,"official":false},"cheapest":{"provider":"edenai","input":1.5,"output":9,"cacheRead":0.15},"blendedRef":3.375,"blendedMin":3.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-19","lastUpdated":"2026-05-19","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-us/"},{"id":"google/gemini-3.5-flash-lite-us","name":"Gemini 3.5 Flash Lite (US)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":0.3,"output":2.5,"cacheRead":0.03,"official":false},"cheapest":{"provider":"edenai","input":0.3,"output":2.5,"cacheRead":0.03},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.5-flash-lite-us/"},{"id":"google/gemini-3.6-flash-us","name":"Gemini 3.6 Flash (US)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video","audio","pdf"],"reference":{"provider":"edenai","input":0.75,"output":3.75,"cacheRead":0.075,"official":false},"cheapest":{"provider":"edenai","input":0.75,"output":3.75,"cacheRead":0.075},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/google/gemini-3.6-flash-us/"},{"id":"zhipuai/zai.glm-4.7-flash-us","name":"GLM-4.7-Flash (US)","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"edenai","input":0.07,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"edenai","input":0.07,"output":0.4,"cacheRead":null},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/zhipuai/zai.glm-4.7-flash-us/"},{"id":"nvidia/nemotron-nano-9b-v2-2","name":"Nemotron Nano 9B v2","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"edenai","input":0.06,"output":0.23,"cacheRead":null,"official":false},"cheapest":{"provider":"edenai","input":0.06,"output":0.23,"cacheRead":null},"blendedRef":0.1025,"blendedMin":0.1025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-18","lastUpdated":"2025-08-18","url":"https://llmpricing.dev/m/nvidia/nemotron-nano-9b-v2-2/"},{"id":"nvidia/nvidia.nemotron-nano-9b-v2-us","name":"Nemotron Nano 9B v2 (US)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"edenai","input":0.06,"output":0.23,"cacheRead":null,"official":false},"cheapest":{"provider":"edenai","input":0.06,"output":0.23,"cacheRead":null},"blendedRef":0.1025,"blendedMin":0.1025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-18","lastUpdated":"2025-08-18","url":"https://llmpricing.dev/m/nvidia/nvidia.nemotron-nano-9b-v2-us/"},{"id":"deepseek/deepseek-v3-turbo","name":"DeepSeek V3 (Turbo)\t","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":64000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.4,"output":1.3,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.4,"output":1.3,"cacheRead":null},"blendedRef":0.625,"blendedMin":0.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-05","lastUpdated":"2025-03-05","url":"https://llmpricing.dev/m/deepseek/deepseek-v3-turbo/"},{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek R1 0528 Qwen3 8B","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.06,"output":0.09,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.06,"output":0.09,"cacheRead":null},"blendedRef":0.0675,"blendedMin":0.0675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":10.3,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-05-29","lastUpdated":"2025-05-29","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-0528-qwen3-8b/"},{"id":"deepseek/deepseek-r1-turbo","name":"DeepSeek R1 (Turbo)\t","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":64000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.7,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.7,"output":2.5,"cacheRead":null},"blendedRef":1.15,"blendedMin":1.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-05","lastUpdated":"2025-03-05","url":"https://llmpricing.dev/m/deepseek/deepseek-r1-turbo/"},{"id":"deepseek/deepseek-ocr-2-2","name":"deepseek/deepseek-ocr-2","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"novita-ai","input":0.03,"output":0.03,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.03,"output":0.03,"cacheRead":null},"blendedRef":0.03,"blendedMin":0.03,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/deepseek/deepseek-ocr-2-2/"},{"id":"paddlepaddle/paddleocr-vl","name":"PaddleOCR-VL","lab":"paddlepaddle","kind":"text","status":"ga","openWeights":true,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"novita-ai","input":0.02,"output":0.02,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.02,"output":0.02,"cacheRead":null},"blendedRef":0.02,"blendedMin":0.02,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-22","lastUpdated":"2025-10-22","url":"https://llmpricing.dev/m/paddlepaddle/paddleocr-vl/"},{"id":"gryphe/mythomax-l2-13b","name":"Mythomax L2 13B","lab":"gryphe","kind":"text","status":"ga","openWeights":true,"context":4096,"contextRange":null,"outputLimit":3200,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.09,"output":0.09,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.09,"output":0.09,"cacheRead":null},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-25","lastUpdated":"2024-04-25","url":"https://llmpricing.dev/m/gryphe/mythomax-l2-13b/"},{"id":"baichuan/baichuan-m2-32b","name":"baichuan-m2-32b","lab":"baichuan","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.07,"output":0.07,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.07,"output":0.07,"cacheRead":null},"blendedRef":0.07,"blendedMin":0.07,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-13","lastUpdated":"2025-08-13","url":"https://llmpricing.dev/m/baichuan/baichuan-m2-32b/"},{"id":"alibaba/qwen3-4b-fp8","name":"Qwen3 4B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":20000,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.03,"output":0.03,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.03,"output":0.03,"cacheRead":null},"blendedRef":0.03,"blendedMin":0.03,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":8.2,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-04-29","lastUpdated":"2025-04-29","url":"https://llmpricing.dev/m/alibaba/qwen3-4b-fp8/"},{"id":"alibaba/qwen3-omni-30b-a3b-instruct","name":"Qwen3 Omni 30B A3B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","video","audio","image"],"reference":{"provider":"novita-ai","input":0.25,"output":0.97,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.25,"output":0.97,"cacheRead":null},"blendedRef":0.43,"blendedMin":0.43,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":4.8,"coding":null,"agentic":null,"speed":93,"ttft":2,"taskCost":null},"usage":null,"releaseDate":"2025-09-24","lastUpdated":"2025-09-24","url":"https://llmpricing.dev/m/alibaba/qwen3-omni-30b-a3b-instruct/"},{"id":"alibaba/qwen3-omni-30b-a3b-thinking","name":"Qwen3 Omni 30B A3B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio","video","image"],"reference":{"provider":"novita-ai","input":0.25,"output":0.97,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.25,"output":0.97,"cacheRead":null},"blendedRef":0.43,"blendedMin":0.43,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-24","lastUpdated":"2025-09-24","url":"https://llmpricing.dev/m/alibaba/qwen3-omni-30b-a3b-thinking/"},{"id":"sao10k/l31-70b-euryale-v2.2","name":"L31 70B Euryale V2.2","lab":"sao10k","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":1.48,"output":1.48,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":1.48,"output":1.48,"cacheRead":null},"blendedRef":1.48,"blendedMin":1.48,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-19","lastUpdated":"2024-09-19","url":"https://llmpricing.dev/m/sao10k/l31-70b-euryale-v2.2/"},{"id":"sao10k/l3-8b-lunaris","name":"Sao10k L3 8B Lunaris\t","lab":"sao10k","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.05,"output":0.05,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.05,"output":0.05,"cacheRead":null},"blendedRef":0.05,"blendedMin":0.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-28","lastUpdated":"2024-11-28","url":"https://llmpricing.dev/m/sao10k/l3-8b-lunaris/"},{"id":"meta/l3-8b-stheno-v3.2-2","name":"L3 8B Stheno V3.2","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.05,"output":0.05,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.05,"output":0.05,"cacheRead":null},"blendedRef":0.05,"blendedMin":0.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-29","lastUpdated":"2024-11-29","url":"https://llmpricing.dev/m/meta/l3-8b-stheno-v3.2-2/"},{"id":"sao10k/l3-70b-euryale-v2.1","name":"L3 70B Euryale V2.1\t","lab":"sao10k","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":1.48,"output":1.48,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":1.48,"output":1.48,"cacheRead":null},"blendedRef":1.48,"blendedMin":1.48,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-06-18","lastUpdated":"2024-06-18","url":"https://llmpricing.dev/m/sao10k/l3-70b-euryale-v2.1/"},{"id":"zhipuai/autoglm-phone-9b-multilingual","name":"AutoGLM-Phone-9B-Multilingual","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"novita-ai","input":0.035,"output":0.138,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.035,"output":0.138,"cacheRead":null},"blendedRef":0.0608,"blendedMin":0.0608,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-10","lastUpdated":"2025-12-10","url":"https://llmpricing.dev/m/zhipuai/autoglm-phone-9b-multilingual/"},{"id":"meta/llama-4-maverick-17b-128e-instruct-fp8-3","name":"Llama 4 Maverick Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"novita-ai","input":0.27,"output":0.85,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.27,"output":0.85,"cacheRead":null},"blendedRef":0.415,"blendedMin":0.415,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-06","lastUpdated":"2025-04-06","url":"https://llmpricing.dev/m/meta/llama-4-maverick-17b-128e-instruct-fp8-3/"},{"id":"meta/llama-3-70b-instruct-2","name":"Llama3 70B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.51,"output":0.74,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.51,"output":0.74,"cacheRead":null},"blendedRef":0.5675,"blendedMin":0.5675,"blendedTrusted":null,"spread":1,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-04-25","lastUpdated":"2024-04-25","url":"https://llmpricing.dev/m/meta/llama-3-70b-instruct-2/"},{"id":"meta/llama-4-scout-17b-16e-instruct-3","name":"Llama 4 Scout Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"novita-ai","input":0.18,"output":0.59,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.18,"output":0.59,"cacheRead":null},"blendedRef":0.2825,"blendedMin":0.2825,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-06","lastUpdated":"2025-04-06","url":"https://llmpricing.dev/m/meta/llama-4-scout-17b-16e-instruct-3/"},{"id":"meta/llama-3-8b-instruct","name":"Llama 3 8B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":8192,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.04,"output":0.04,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.04,"output":0.04,"cacheRead":null},"blendedRef":0.04,"blendedMin":0.04,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-04-25","lastUpdated":"2024-04-25","url":"https://llmpricing.dev/m/meta/llama-3-8b-instruct/"},{"id":"baidu/ernie-4.5-21b-a3b-thinking-2","name":"ERNIE-4.5-21B-A3B-Thinking","lab":"baidu","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.07,"output":0.28,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.07,"output":0.28,"cacheRead":null},"blendedRef":0.1225,"blendedMin":0.1225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-19","lastUpdated":"2025-09-19","url":"https://llmpricing.dev/m/baidu/ernie-4.5-21b-a3b-thinking-2/"},{"id":"baidu/ernie-4.5-vl-28b-a3b-thinking","name":"ERNIE-4.5-VL-28B-A3B-Thinking","lab":"baidu","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"novita-ai","input":0.39,"output":0.39,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.39,"output":0.39,"cacheRead":null},"blendedRef":0.39,"blendedMin":0.39,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-26","lastUpdated":"2025-11-26","url":"https://llmpricing.dev/m/baidu/ernie-4.5-vl-28b-a3b-thinking/"},{"id":"baidu/ernie-4.5-vl-28b-a3b","name":"ERNIE 4.5 VL 28B A3B","lab":"baidu","kind":"text","status":"ga","openWeights":true,"context":30000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"novita-ai","input":0.14,"output":0.56,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.14,"output":0.56,"cacheRead":null},"blendedRef":0.245,"blendedMin":0.245,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2026-06-14","url":"https://llmpricing.dev/m/baidu/ernie-4.5-vl-28b-a3b/"},{"id":"baidu/ernie-4.5-21b-a3b","name":"ERNIE 4.5 21B A3B","lab":"baidu","kind":"text","status":"ga","openWeights":true,"context":120000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"novita-ai","input":0.07,"output":0.28,"cacheRead":null,"official":false},"cheapest":{"provider":"novita-ai","input":0.07,"output":0.28,"cacheRead":null},"blendedRef":0.1225,"blendedMin":0.1225,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/baidu/ernie-4.5-21b-a3b/"},{"id":"upstage/solar-mini","name":"solar-mini","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"upstage","input":0.15,"output":0.15,"cacheRead":null,"official":true},"cheapest":{"provider":"upstage","input":0.15,"output":0.15,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":6,"coding":null,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2024-06-12","lastUpdated":"2025-04-22","url":"https://llmpricing.dev/m/upstage/solar-mini/"},{"id":"misc/custom","name":"Custom Model","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/custom/"},{"id":"alibaba/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B FP8","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":40960,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.2,"output":0.8,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.2,"output":0.8,"cacheRead":null},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-28","lastUpdated":"2025-04-28","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-fp8/"},{"id":"misc/auto-3","name":"Auto Route","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2024-01-01","url":"https://llmpricing.dev/m/misc/auto-3/"},{"id":"minimax/minimax-text-01-2","name":"MiniMax Text 01","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.2,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.2,"output":1.1,"cacheRead":null},"blendedRef":0.425,"blendedMin":0.425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-15","lastUpdated":"2025-01-15","url":"https://llmpricing.dev/m/minimax/minimax-text-01-2/"},{"id":"misc/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.06,"output":0.18,"cacheRead":0.012,"official":false},"cheapest":{"provider":"llmgateway","input":0.06,"output":0.18,"cacheRead":0.012},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-02","lastUpdated":"2026-08-02","url":"https://llmpricing.dev/m/misc/ling-3.0-flash/"},{"id":"alibaba/qwen-plus-latest-2","name":"Qwen Plus Latest","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.4,"output":1.2,"cacheRead":0.08,"official":false},"cheapest":{"provider":"llmgateway","input":0.4,"output":1.2,"cacheRead":0.08},"blendedRef":0.6,"blendedMin":0.6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-25","lastUpdated":"2025-01-25","url":"https://llmpricing.dev/m/alibaba/qwen-plus-latest-2/"},{"id":"zhipuai/glm-4-32b-0414-128k-2","name":"GLM-4 32B (0414-128k)","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.1,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.1,"output":0.1,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-14","lastUpdated":"2025-04-14","url":"https://llmpricing.dev/m/zhipuai/glm-4-32b-0414-128k-2/"},{"id":"misc/seed-1-8-251228","name":"Seed 1.8 (251228)","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway","input":0.25,"output":2,"cacheRead":0.05},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-18","lastUpdated":"2025-12-18","url":"https://llmpricing.dev/m/misc/seed-1-8-251228/"},{"id":"misc/seed-1-6-250915","name":"Seed 1.6 (250915)","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway","input":0.25,"output":2,"cacheRead":0.05},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-15","lastUpdated":"2025-09-15","url":"https://llmpricing.dev/m/misc/seed-1-6-250915/"},{"id":"meta/llama-3.2-11b-instruct-2","name":"Llama 3.2 11B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.07,"output":0.33,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.07,"output":0.33,"cacheRead":null},"blendedRef":0.135,"blendedMin":0.135,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-11b-instruct-2/"},{"id":"misc/seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715)","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.07,"output":0.3,"cacheRead":0.015,"official":false},"cheapest":{"provider":"llmgateway","input":0.07,"output":0.3,"cacheRead":0.015},"blendedRef":0.1275,"blendedMin":0.1275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-26","lastUpdated":"2025-07-26","url":"https://llmpricing.dev/m/misc/seed-1-6-flash-250715/"},{"id":"misc/seed-1-6-250615","name":"Seed 1.6 (250615)","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.25,"output":2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"llmgateway","input":0.25,"output":2,"cacheRead":0.05},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-25","lastUpdated":"2025-06-25","url":"https://llmpricing.dev/m/misc/seed-1-6-250615/"},{"id":"mistral/codestral-2508-3","name":"Codestral","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.3,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.3,"output":0.9,"cacheRead":null},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-30","lastUpdated":"2025-07-30","url":"https://llmpricing.dev/m/mistral/codestral-2508-3/"},{"id":"alibaba/qwen-coder-plus-2","name":"Qwen Coder Plus","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"llmgateway","input":0.502,"output":1.004,"cacheRead":null,"official":false},"cheapest":{"provider":"llmgateway","input":0.502,"output":1.004,"cacheRead":null},"blendedRef":0.6275,"blendedMin":0.6275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-18","lastUpdated":"2024-09-18","url":"https://llmpricing.dev/m/alibaba/qwen-coder-plus-2/"},{"id":"alibaba/qwen3-vl-flash-2","name":"Qwen3 VL Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"llmgateway","input":0.05,"output":0.4,"cacheRead":0.01,"official":false},"cheapest":{"provider":"llmgateway","input":0.05,"output":0.4,"cacheRead":0.01},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-09","lastUpdated":"2025-10-09","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-flash-2/"},{"id":"nvidia/nemotron-3-nano-omni-30b-tee","name":"Nemotron 3 Nano Omni 30B TEE","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":0,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"chutes","input":0.0245,"output":0.0978,"cacheRead":0.0024499999999999995,"official":false},"cheapest":{"provider":"chutes","input":0.0245,"output":0.0978,"cacheRead":0.0024499999999999995},"blendedRef":0.0428,"blendedMin":0.0428,"blendedTrusted":0.0428,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-23","lastUpdated":"2026-07-23","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni-30b-tee/"},{"id":"google/gemma-4-31b-turbo-tee","name":"gemma 4 31B turbo TEE","lab":"google","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"chutes","input":0.12,"output":0.37,"cacheRead":0.011999999999999997,"official":false},"cheapest":{"provider":"chutes","input":0.12,"output":0.37,"cacheRead":0.011999999999999997},"blendedRef":0.1825,"blendedMin":0.1825,"blendedTrusted":0.1825,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-31b-turbo-tee/"},{"id":"mistral/mistral-nemo-instruct-2407-tee","name":"Mistral Nemo Instruct 2407 TEE","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"chutes","input":0.0245,"output":0.0978,"cacheRead":0.0024499999999999995,"official":false},"cheapest":{"provider":"chutes","input":0.0245,"output":0.0978,"cacheRead":0.0024499999999999995},"blendedRef":0.0428,"blendedMin":0.0428,"blendedTrusted":0.0428,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-01","lastUpdated":"2024-07-01","url":"https://llmpricing.dev/m/mistral/mistral-nemo-instruct-2407-tee/"},{"id":"deepseek/deepseek-v4-flash-0731-tee","name":"DeepSeek V4 Flash 0731 TEE","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"chutes","input":0.14,"output":0.28,"cacheRead":0.013999999999999999,"official":false},"cheapest":{"provider":"chutes","input":0.14,"output":0.28,"cacheRead":0.013999999999999999},"blendedRef":0.175,"blendedMin":0.175,"blendedTrusted":0.175,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-31","lastUpdated":"2026-08-02","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-0731-tee/"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507-tee","name":"Qwen3 235B A22B Thinking 2507 TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"chutes","input":0.2989,"output":1.1957,"cacheRead":0.029889999999999993,"official":false},"cheapest":{"provider":"chutes","input":0.2989,"output":1.1957,"cacheRead":0.029889999999999993},"blendedRef":0.5231,"blendedMin":0.5231,"blendedTrusted":0.5231,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07","lastUpdated":"2026-06-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-thinking-2507-tee/"},{"id":"alibaba/qwen3-32b-tee","name":"Qwen3 32B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":40960,"contextRange":null,"outputLimit":40960,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"chutes","input":0.104,"output":0.416,"cacheRead":0.010399999999999998,"official":false},"cheapest":{"provider":"chutes","input":0.104,"output":0.416,"cacheRead":0.010399999999999998},"blendedRef":0.182,"blendedMin":0.182,"blendedTrusted":0.182,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04","lastUpdated":"2025-04","url":"https://llmpricing.dev/m/alibaba/qwen3-32b-tee/"},{"id":"alibaba/qwen3.8-27b-tee","name":"Qwen3.8 27B TEE","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"chutes","input":0.4,"output":3,"cacheRead":0.039999999999999994,"official":false},"cheapest":{"provider":"chutes","input":0.4,"output":3,"cacheRead":0.039999999999999994},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":1.05,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-16","lastUpdated":"2026-08-16","url":"https://llmpricing.dev/m/alibaba/qwen3.8-27b-tee/"},{"id":"deepseek/deepseek-v4-pro-lightning","name":"DeepSeek V4 Pro Lightning","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"crof","input":0.8,"output":1.6,"cacheRead":0.02,"official":false},"cheapest":{"provider":"crof","input":0.8,"output":1.6,"cacheRead":0.02},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-24","lastUpdated":"2026-04-24","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-pro-lightning/"},{"id":"moonshotai/kimi-k2.5-lightning","name":"Kimi K2.5 (Lightning)","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"crof","input":1,"output":3,"cacheRead":0.2,"official":false},"cheapest":{"provider":"crof","input":1,"output":3,"cacheRead":0.2},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-06","lastUpdated":"2026-02-06","url":"https://llmpricing.dev/m/moonshotai/kimi-k2.5-lightning/"},{"id":"misc/greg-rp","name":"Greg (Roleplay)","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":229376,"contextRange":null,"outputLimit":229376,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"crof","input":0.1,"output":0.3,"cacheRead":0.02,"official":false},"cheapest":{"provider":"crof","input":0.1,"output":0.3,"cacheRead":0.02},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/misc/greg-rp/"},{"id":"misc/greg-1-mini","name":"Greg 1 Mini","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":229376,"contextRange":null,"outputLimit":229376,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"crof","input":0.07,"output":0.15,"cacheRead":0.01,"official":false},"cheapest":{"provider":"crof","input":0.07,"output":0.15,"cacheRead":0.01},"blendedRef":0.09,"blendedMin":0.09,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/misc/greg-1-mini/"},{"id":"moonshotai/kimi-k3-eco","name":"Kimi K3 Eco","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"crof","input":1,"output":4,"cacheRead":0.1,"official":false},"cheapest":{"provider":"crof","input":1,"output":4,"cacheRead":0.1},"blendedRef":1.75,"blendedMin":1.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k3-eco/"},{"id":"deepseek/deepseek-v4-flash-0731-2","name":"DeepSeek V4 Flash (New)","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"crof","input":0.12,"output":0.21,"cacheRead":0.003,"official":false},"cheapest":{"provider":"crof","input":0.12,"output":0.21,"cacheRead":0.003},"blendedRef":0.1425,"blendedMin":0.1425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-31","lastUpdated":"2026-07-31","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-0731-2/"},{"id":"misc/v0-1.0-md","name":"v0-1.0-md","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"v0","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"v0","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-22","lastUpdated":"2025-05-22","url":"https://llmpricing.dev/m/misc/v0-1.0-md/"},{"id":"misc/v0-1.5-md","name":"v0-1.5-md","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"v0","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"v0","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-09","lastUpdated":"2025-06-09","url":"https://llmpricing.dev/m/misc/v0-1.5-md/"},{"id":"misc/v0-1.5-lg","name":"v0-1.5-lg","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":512000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"v0","input":15,"output":75,"cacheRead":null,"official":false},"cheapest":{"provider":"v0","input":15,"output":75,"cacheRead":null},"blendedRef":30,"blendedMin":30,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-09","lastUpdated":"2025-06-09","url":"https://llmpricing.dev/m/misc/v0-1.5-lg/"},{"id":"sdaia/allam-2-7b","name":"ALLaM-2-7b","lab":"sdaia","kind":"text","status":"ga","openWeights":true,"context":4096,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"groq","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-01-23","lastUpdated":"2025-01-23","url":"https://llmpricing.dev/m/sdaia/allam-2-7b/"},{"id":"openai/gpt-oss-safeguard-20b-2","name":"Safety GPT OSS 20B","lab":"openai","kind":"text","status":"beta","openWeights":true,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"groq","input":0.075,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"groq","input":0.075,"output":0.3,"cacheRead":null},"blendedRef":0.1312,"blendedMin":0.1312,"blendedTrusted":0.1312,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-29","lastUpdated":"2026-06-29","url":"https://llmpricing.dev/m/openai/gpt-oss-safeguard-20b-2/"},{"id":"meta/llama-prompt-guard-2-86m-2","name":"Prompt Guard 2 86M","lab":"meta","kind":"classify","status":"beta","openWeights":true,"context":512,"contextRange":null,"outputLimit":512,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"groq","input":0.04,"output":0.04,"cacheRead":null,"official":false},"cheapest":{"provider":"groq","input":0.04,"output":0.04,"cacheRead":null},"blendedRef":0.04,"blendedMin":0.04,"blendedTrusted":0.04,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-29","lastUpdated":"2025-05-29","url":"https://llmpricing.dev/m/meta/llama-prompt-guard-2-86m-2/"},{"id":"meta/llama-prompt-guard-2-22m-2","name":"Llama Prompt Guard 2 22M","lab":"meta","kind":"classify","status":"beta","openWeights":true,"context":512,"contextRange":null,"outputLimit":512,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"groq","input":0.03,"output":0.03,"cacheRead":null,"official":false},"cheapest":{"provider":"groq","input":0.03,"output":0.03,"cacheRead":null},"blendedRef":0.03,"blendedMin":0.03,"blendedTrusted":0.03,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-29","lastUpdated":"2025-05-29","url":"https://llmpricing.dev/m/meta/llama-prompt-guard-2-22m-2/"},{"id":"groq/compound-mini","name":"Compound Mini","lab":"groq","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-04","lastUpdated":"2025-09-04","url":"https://llmpricing.dev/m/groq/compound-mini/"},{"id":"groq/compound","name":"Compound","lab":"groq","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-09-04","lastUpdated":"2025-09-04","url":"https://llmpricing.dev/m/groq/compound/"},{"id":"canopylabs/orpheus-arabic-saudi","name":"Canopy Labs Orpheus Arabic Saudi","lab":"canopylabs","kind":"audio","status":"beta","openWeights":false,"context":4000,"contextRange":null,"outputLimit":50000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-16","lastUpdated":"2025-12-16","url":"https://llmpricing.dev/m/canopylabs/orpheus-arabic-saudi/"},{"id":"canopylabs/orpheus-v1-english","name":"Canopy Labs Orpheus V1 English","lab":"canopylabs","kind":"audio","status":"beta","openWeights":false,"context":4000,"contextRange":null,"outputLimit":50000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2025-12-19","lastUpdated":"2025-12-19","url":"https://llmpricing.dev/m/canopylabs/orpheus-v1-english/"},{"id":"alibaba/qwen3.8-2.4t-a95b-nvfp4","name":"Qwen3.8 2.4T A95B (NVFP4)","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"runinfra","input":2,"output":6,"cacheRead":0.2,"official":false},"cheapest":{"provider":"runinfra","input":2,"output":6,"cacheRead":0.2},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/alibaba/qwen3.8-2.4t-a95b-nvfp4/"},{"id":"anthropic/duo-chat-opus-4-5","name":"Agentic Chat (Claude Opus 4.5)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-08","lastUpdated":"2026-01-08","url":"https://llmpricing.dev/m/anthropic/duo-chat-opus-4-5/"},{"id":"openai/duo-chat-gpt-5-2-codex","name":"Agentic Chat (GPT-5.2 Codex)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-22","lastUpdated":"2026-01-22","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-2-codex/"},{"id":"openai/duo-chat-gpt-5-2","name":"Agentic Chat (GPT-5.2)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-23","lastUpdated":"2026-01-23","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-2/"},{"id":"anthropic/duo-chat-sonnet-4-5","name":"Agentic Chat (Claude Sonnet 4.5)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-08","lastUpdated":"2026-01-08","url":"https://llmpricing.dev/m/anthropic/duo-chat-sonnet-4-5/"},{"id":"openai/duo-chat-gpt-5-4-mini","name":"Agentic Chat (GPT-5.4 Mini)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-4-mini/"},{"id":"openai/duo-chat-gpt-5-5","name":"Agentic Chat (GPT-5.5)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-5/"},{"id":"anthropic/duo-chat-haiku-4-5","name":"Agentic Chat (Claude Haiku 4.5)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-08","lastUpdated":"2026-01-08","url":"https://llmpricing.dev/m/anthropic/duo-chat-haiku-4-5/"},{"id":"openai/duo-chat-gpt-5-6-sol","name":"Agentic Chat (GPT-5.6 Sol)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-6-sol/"},{"id":"openai/duo-chat-gpt-5-6-luna","name":"Agentic Chat (GPT-5.6 Luna)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-6-luna/"},{"id":"anthropic/duo-chat-opus-4-8","name":"Agentic Chat (Claude Opus 4.8)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-28","lastUpdated":"2026-05-28","url":"https://llmpricing.dev/m/anthropic/duo-chat-opus-4-8/"},{"id":"anthropic/duo-chat-fable-5","name":"Agentic Chat (Claude Fable 5)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/duo-chat-fable-5/"},{"id":"openai/duo-chat-gpt-5-6-terra","name":"Agentic Chat (GPT-5.6 Terra)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-09","lastUpdated":"2026-07-09","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-6-terra/"},{"id":"openai/duo-chat-gpt-5-1","name":"Agentic Chat (GPT-5.1)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-22","lastUpdated":"2026-01-22","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-1/"},{"id":"openai/duo-chat-gpt-5-codex","name":"Agentic Chat (GPT-5 Codex)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-22","lastUpdated":"2026-01-22","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-codex/"},{"id":"anthropic/duo-chat-opus-4-7","name":"Agentic Chat (Claude Opus 4.7)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-16","lastUpdated":"2026-04-16","url":"https://llmpricing.dev/m/anthropic/duo-chat-opus-4-7/"},{"id":"anthropic/duo-chat-sonnet-5","name":"Agentic Chat (Claude Sonnet 5)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-30","lastUpdated":"2026-06-30","url":"https://llmpricing.dev/m/anthropic/duo-chat-sonnet-5/"},{"id":"openai/duo-chat-gpt-5-mini","name":"Agentic Chat (GPT-5 Mini)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-01-22","lastUpdated":"2026-01-22","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-mini/"},{"id":"openai/duo-chat-gpt-5-4-nano","name":"Agentic Chat (GPT-5.4 Nano)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-17","lastUpdated":"2026-03-17","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-4-nano/"},{"id":"anthropic/duo-chat-opus-5","name":"Agentic Chat (Claude Opus 5)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-24","lastUpdated":"2026-07-24","url":"https://llmpricing.dev/m/anthropic/duo-chat-opus-5/"},{"id":"anthropic/duo-chat-opus-4-6","name":"Agentic Chat (Claude Opus 4.6)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/anthropic/duo-chat-opus-4-6/"},{"id":"openai/duo-chat-gpt-5-4","name":"Agentic Chat (GPT-5.4)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-05","lastUpdated":"2026-03-05","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-4/"},{"id":"anthropic/duo-chat-sonnet-4-6","name":"Agentic Chat (Claude Sonnet 4.6)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-17","lastUpdated":"2026-02-17","url":"https://llmpricing.dev/m/anthropic/duo-chat-sonnet-4-6/"},{"id":"openai/duo-chat-gpt-5-3-codex","name":"Agentic Chat (GPT-5.3 Codex)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"gitlab","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/duo-chat-gpt-5-3-codex/"},{"id":"zhipuai/glm-5.2-fp4","name":"GLM 5.2 FP4","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"coralbricks","input":1.12,"output":4.4,"cacheRead":0,"official":false},"cheapest":{"provider":"coralbricks","input":1.12,"output":4.4,"cacheRead":0},"blendedRef":1.94,"blendedMin":1.94,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-13","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/zhipuai/glm-5.2-fp4/"},{"id":"motif-technologies/motif-3","name":"Motif 3","lab":"motif-technologies","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"aiand","input":0.5,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"aiand","input":0.5,"output":2,"cacheRead":null},"blendedRef":0.875,"blendedMin":0.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":47.4,"coding":63.5,"agentic":37.6,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/motif-technologies/motif-3/"},{"id":"microsoft/mai-code-1-flash","name":"MAI-Code-1-Flash","lab":"microsoft","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"github-copilot","input":0.75,"output":4.5,"cacheRead":0.075,"official":false},"cheapest":{"provider":"github-copilot","input":0.75,"output":4.5,"cacheRead":0.075},"blendedRef":1.6875,"blendedMin":1.6875,"blendedTrusted":1.6875,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-02","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/microsoft/mai-code-1-flash/"},{"id":"microsoft/mai-code-1.1-flash","name":"MAI-Code-1.1-Flash","lab":"microsoft","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"github-copilot","input":0.2,"output":1.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"github-copilot","input":0.2,"output":1.2,"cacheRead":0.02},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":0.45,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/microsoft/mai-code-1.1-flash/"},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek Chat V3.1","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":164000,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"tensorx","input":0.2,"output":0.8,"cacheRead":0.05,"official":false},"cheapest":{"provider":"tensorx","input":0.2,"output":0.8,"cacheRead":0.05},"blendedRef":0.35,"blendedMin":0.35,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/deepseek/deepseek-chat-v3.1/"},{"id":"deepcogito/cogito-v2.1-671b-2","name":"Deep Cogito: Cogito v2.1 671B","lab":"deepcogito","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":1.25,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1.25,"output":1.25,"cacheRead":null},"blendedRef":1.25,"blendedMin":1.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-13","lastUpdated":"2025-11-13","url":"https://llmpricing.dev/m/deepcogito/cogito-v2.1-671b-2/"},{"id":"tencent/hy-mt2-30b-a3b-2","name":"Tencent: Hy-MT2-30B-A3B","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.074,"output":0.295,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.074,"output":0.295,"cacheRead":null},"blendedRef":0.1292,"blendedMin":0.1292,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/tencent/hy-mt2-30b-a3b-2/"},{"id":"tencent/hy-mt2-1.8b-2","name":"Tencent: Hy-MT2-1.8B","lab":"tencent","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.044,"output":0.177,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.044,"output":0.177,"cacheRead":null},"blendedRef":0.0773,"blendedMin":0.0773,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-20","lastUpdated":"2026-08-20","url":"https://llmpricing.dev/m/tencent/hy-mt2-1.8b-2/"},{"id":"tencent/hy3-free-2","name":"Tencent: Hy3 (free)","lab":"tencent","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-06","lastUpdated":"2026-07-06","url":"https://llmpricing.dev/m/tencent/hy3-free-2/"},{"id":"anthropic/claude-opus-latest-2","name":"Anthropic: Claude Opus Latest","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"kilo","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/anthropic/claude-opus-latest-2/"},{"id":"anthropic/claude-fable-latest-2","name":"Anthropic: Claude Fable Latest ($$$$)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":10,"output":50,"cacheRead":1,"official":false},"cheapest":{"provider":"kilo","input":10,"output":50,"cacheRead":1},"blendedRef":20,"blendedMin":20,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-09","lastUpdated":"2026-06-09","url":"https://llmpricing.dev/m/anthropic/claude-fable-latest-2/"},{"id":"xai/grok-latest-2","name":"xAI: Grok Latest","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":500000,"contextRange":null,"outputLimit":500000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":2,"output":6,"cacheRead":0.5,"official":false},"cheapest":{"provider":"kilo","input":2,"output":6,"cacheRead":0.5},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-08","lastUpdated":"2026-07-08","url":"https://llmpricing.dev/m/xai/grok-latest-2/"},{"id":"nvidia/nemotron-3-super-120b-a12b-free-3","name":"NVIDIA: Nemotron 3 Super (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-03-11","lastUpdated":"2026-03-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3-super-120b-a12b-free-3/"},{"id":"nvidia/nemotron-3.5-lightning-free-2","name":"NVIDIA: Nemotron 3.5 Lightning (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-lightning-free-2/"},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-free-2","name":"NVIDIA: Nemotron 3 Nano Omni (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","video","audio"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-04-28","lastUpdated":"2026-04-28","url":"https://llmpricing.dev/m/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-free-2/"},{"id":"nvidia/nemotron-3.5-content-safety-free-2","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3.5-content-safety-free-2/"},{"id":"nvidia/nemotron-3-ultra-550b-a55b-free-2","name":"NVIDIA: Nemotron 3 Ultra (free)","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-04","lastUpdated":"2026-06-04","url":"https://llmpricing.dev/m/nvidia/nemotron-3-ultra-550b-a55b-free-2/"},{"id":"meta/aion-rp-llama-3.1-8b-3","name":"AionLabs: Aion-RP 1.0 (8B)","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.8,"output":1.6,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.8,"output":1.6,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-04","lastUpdated":"2025-02-04","url":"https://llmpricing.dev/m/meta/aion-rp-llama-3.1-8b-3/"},{"id":"microsoft/phi-4-2","name":"Microsoft: Phi 4","lab":"microsoft","kind":"text","status":"ga","openWeights":false,"context":16384,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.07,"output":0.14,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.07,"output":0.14,"cacheRead":null},"blendedRef":0.0875,"blendedMin":0.0875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-10","lastUpdated":"2025-01-10","url":"https://llmpricing.dev/m/microsoft/phi-4-2/"},{"id":"deepseek/deepseek-chat-v3.1-2","name":"DeepSeek: DeepSeek V3.1","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.27,"output":1,"cacheRead":0.135,"official":false},"cheapest":{"provider":"kilo","input":0.27,"output":1,"cacheRead":0.135},"blendedRef":0.4525,"blendedMin":0.4525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-21","lastUpdated":"2025-08-21","url":"https://llmpricing.dev/m/deepseek/deepseek-chat-v3.1-2/"},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","lab":"deepseek","kind":"text","status":"ga","openWeights":false,"context":163840,"contextRange":null,"outputLimit":163840,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.27,"output":1.12,"cacheRead":0.135,"official":false},"cheapest":{"provider":"kilo","input":0.27,"output":1.12,"cacheRead":0.135},"blendedRef":0.4825,"blendedMin":0.4825,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-24","lastUpdated":"2025-03-24","url":"https://llmpricing.dev/m/deepseek/deepseek-chat-v3-0324/"},{"id":"arcee-ai/virtuoso-large-2","name":"Arcee AI: Virtuoso Large","lab":"arcee-ai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.75,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.75,"output":1.2,"cacheRead":null},"blendedRef":0.8625,"blendedMin":0.8625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-05","lastUpdated":"2025-05-05","url":"https://llmpricing.dev/m/arcee-ai/virtuoso-large-2/"},{"id":"google/gemini-2.5-pro-preview-05-06-2","name":"Google: Gemini 2.5 Pro Preview 05-06","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65535,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf","audio","video"],"reference":{"provider":"kilo","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"kilo","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-07","lastUpdated":"2025-05-07","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-preview-05-06-2/"},{"id":"google/gemma-2-27b-it-2","name":"Google: Gemma 2 27B","lab":"google","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.65,"output":0.65,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.65,"output":0.65,"cacheRead":null},"blendedRef":0.65,"blendedMin":0.65,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-13","lastUpdated":"2024-07-13","url":"https://llmpricing.dev/m/google/gemma-2-27b-it-2/"},{"id":"google/gemma-3-4b-it-3","name":"Google: Gemma 3 4B","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.05,"output":0.1,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.05,"output":0.1,"cacheRead":null},"blendedRef":0.0625,"blendedMin":0.0625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/google/gemma-3-4b-it-3/"},{"id":"google/gemma-3n-e4b-it-4","name":"Google: Gemma 3n 4B","lab":"google","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":6554,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.06,"output":0.12,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.06,"output":0.12,"cacheRead":null},"blendedRef":0.075,"blendedMin":0.075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-20","lastUpdated":"2025-05-20","url":"https://llmpricing.dev/m/google/gemma-3n-e4b-it-4/"},{"id":"google/gemma-3-27b-it-3","name":"Google: Gemma 3 27B","lab":"google","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.08,"output":0.16,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.08,"output":0.16,"cacheRead":null},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-12","lastUpdated":"2025-03-12","url":"https://llmpricing.dev/m/google/gemma-3-27b-it-3/"},{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","lab":"google","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["pdf","image","text","audio"],"reference":{"provider":"kilo","input":1.25,"output":10,"cacheRead":0.125,"official":false},"cheapest":{"provider":"kilo","input":1.25,"output":10,"cacheRead":0.125},"blendedRef":3.4375,"blendedMin":3.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-05","lastUpdated":"2025-06-05","url":"https://llmpricing.dev/m/google/gemini-2.5-pro-preview/"},{"id":"inception/mercury-2-2","name":"Inception: Mercury 2","lab":"inception","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":50000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.25,"output":0.75,"cacheRead":0.025,"official":false},"cheapest":{"provider":"kilo","input":0.25,"output":0.75,"cacheRead":0.025},"blendedRef":0.375,"blendedMin":0.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-04","lastUpdated":"2026-03-04","url":"https://llmpricing.dev/m/inception/mercury-2-2/"},{"id":"misc/free-2","name":"OpenRouter Free Models Router","lab":"misc","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-02-01","lastUpdated":"2026-02-01","url":"https://llmpricing.dev/m/misc/free-2/"},{"id":"poolside/laguna-xs-2.1-free-2","name":"Poolside: Laguna XS 2.1 (free)","lab":"poolside","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-02","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/poolside/laguna-xs-2.1-free-2/"},{"id":"poolside/laguna-s-2.1-2","name":"Poolside: Laguna S 2.1","lab":"poolside","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":0.01,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":0.01},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/poolside/laguna-s-2.1-2/"},{"id":"poolside/laguna-xs-2.1-2","name":"Poolside: Laguna XS 2.1","lab":"poolside","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":0.05,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":0.05},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-02","lastUpdated":"2026-07-02","url":"https://llmpricing.dev/m/poolside/laguna-xs-2.1-2/"},{"id":"poolside/laguna-s-2.1-free-2","name":"Poolside: Laguna S 2.1 (free)","lab":"poolside","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-21","lastUpdated":"2026-07-21","url":"https://llmpricing.dev/m/poolside/laguna-s-2.1-free-2/"},{"id":"xai/grok-4.20-2","name":"SpaceXAI: Grok 4.20","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"kilo","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-31","lastUpdated":"2026-03-31","url":"https://llmpricing.dev/m/xai/grok-4.20-2/"},{"id":"xai/grok-4.20-multi-agent-2","name":"SpaceXAI: Grok 4.20 Multi-Agent","lab":"xai","kind":"text","status":"ga","openWeights":false,"context":2000000,"contextRange":null,"outputLimit":2000000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":1.25,"output":2.5,"cacheRead":0.2,"official":false},"cheapest":{"provider":"kilo","input":1.25,"output":2.5,"cacheRead":0.2},"blendedRef":1.5625,"blendedMin":1.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-31","lastUpdated":"2026-03-31","url":"https://llmpricing.dev/m/xai/grok-4.20-multi-agent-2/"},{"id":"perceptron/perceptron-mk1-2","name":"Perceptron: Perceptron Mk1","lab":"perceptron","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":0.15,"output":1.5,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.15,"output":1.5,"cacheRead":null},"blendedRef":0.4875,"blendedMin":0.4875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-12","lastUpdated":"2026-05-12","url":"https://llmpricing.dev/m/perceptron/perceptron-mk1-2/"},{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text","video"],"reference":{"provider":"kilo","input":0.075,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.075,"output":0.3,"cacheRead":null},"blendedRef":0.1312,"blendedMin":0.1312,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/bytedance-seed/seed-1.6-flash/"},{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text","video"],"reference":{"provider":"kilo","input":0.25,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.25,"output":2,"cacheRead":null},"blendedRef":0.6875,"blendedMin":0.6875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-23","lastUpdated":"2025-12-23","url":"https://llmpricing.dev/m/bytedance-seed/seed-1.6/"},{"id":"bytedance-seed/seed-2-1-turbo-2","name":"ByteDance Seed: Seed 2.1 Turbo","lab":"bytedance-seed","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":0.5,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.5,"output":2.5,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-12","url":"https://llmpricing.dev/m/bytedance-seed/seed-2-1-turbo-2/"},{"id":"moonshotai/kimi-k2-3","name":"MoonshotAI: Kimi K2 0711","lab":"moonshotai","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":100352,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.57,"output":2.3,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.57,"output":2.3,"cacheRead":null},"blendedRef":1.0025,"blendedMin":1.0025,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-11","lastUpdated":"2025-07-11","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-3/"},{"id":"moonshotai/kimi-k2-0905-2","name":"MoonshotAI: Kimi K2 0905","lab":"moonshotai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":100352,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.6,"output":2.5,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.6,"output":2.5,"cacheRead":null},"blendedRef":1.075,"blendedMin":1.075,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-04","lastUpdated":"2025-09-04","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-0905-2/"},{"id":"cohere/command-a","name":"Cohere: Command A","lab":"cohere","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-13","lastUpdated":"2025-03-13","url":"https://llmpricing.dev/m/cohere/command-a/"},{"id":"cohere/north-mini-code-free-2","name":"Cohere: North Mini Code (free)","lab":"cohere","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-17","lastUpdated":"2026-06-17","url":"https://llmpricing.dev/m/cohere/north-mini-code-free-2/"},{"id":"bytedance/ui-tars-1.5-7b-2","name":"ByteDance: UI-TARS 7B ","lab":"bytedance","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":2048,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":0.1,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.2,"cacheRead":0.1},"blendedRef":0.125,"blendedMin":0.125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-22","lastUpdated":"2025-07-22","url":"https://llmpricing.dev/m/bytedance/ui-tars-1.5-7b-2/"},{"id":"openai/gpt-audio-2","name":"OpenAI: GPT Audio","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio","pdf"],"reference":{"provider":"kilo","input":2.5,"output":10,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":2.5,"output":10,"cacheRead":null},"blendedRef":4.375,"blendedMin":4.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/openai/gpt-audio-2/"},{"id":"openai/gpt-3.5-turbo-16k-2","name":"OpenAI: GPT-3.5 Turbo 16k","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":16385,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":3,"output":4,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":3,"output":4,"cacheRead":null},"blendedRef":3.25,"blendedMin":3.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-08-28","lastUpdated":"2023-08-28","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-16k-2/"},{"id":"openai/gpt-4-turbo-preview-2","name":"OpenAI: GPT-4 Turbo Preview ($$$$)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":10,"output":30,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":10,"output":30,"cacheRead":null},"blendedRef":15,"blendedMin":15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/gpt-4-turbo-preview-2/"},{"id":"openai/gpt-3.5-turbo-instruct-2","name":"OpenAI: GPT-3.5 Turbo Instruct","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":4095,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":1.5,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1.5,"output":2,"cacheRead":null},"blendedRef":1.625,"blendedMin":1.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-09-28","lastUpdated":"2023-09-28","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-instruct-2/"},{"id":"openai/gpt-4o-mini-2024-07-18-2","name":"OpenAI: GPT-4o-mini (2024-07-18)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":0.15,"output":0.6,"cacheRead":0.075,"official":false},"cheapest":{"provider":"kilo","input":0.15,"output":0.6,"cacheRead":0.075},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-18","lastUpdated":"2024-07-18","url":"https://llmpricing.dev/m/openai/gpt-4o-mini-2024-07-18-2/"},{"id":"openai/gpt-5.6-sol-discounted","name":"OpenAI: GPT-5.6 Sol (50% off)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":1050000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":2.5,"output":15,"cacheRead":0.25,"official":false},"cheapest":{"provider":"kilo","input":2.5,"output":15,"cacheRead":0.25},"blendedRef":5.625,"blendedMin":5.625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/openai/gpt-5.6-sol-discounted/"},{"id":"openai/gpt-5-image-mini-2","name":"OpenAI: GPT-5 Image Mini","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["pdf","image","text"],"reference":{"provider":"kilo","input":2.5,"output":2,"cacheRead":0.25,"official":false},"cheapest":{"provider":"kilo","input":2.5,"output":2,"cacheRead":0.25},"blendedRef":2.375,"blendedMin":2.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-16","lastUpdated":"2025-10-16","url":"https://llmpricing.dev/m/openai/gpt-5-image-mini-2/"},{"id":"openai/gpt-5.4-image-2-2","name":"OpenAI: GPT-5.4 Image 2","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":272000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["image","text","pdf"],"reference":{"provider":"kilo","input":8,"output":15,"cacheRead":2,"official":false},"cheapest":{"provider":"kilo","input":8,"output":15,"cacheRead":2},"blendedRef":9.75,"blendedMin":9.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/openai/gpt-5.4-image-2-2/"},{"id":"openai/gpt-audio-mini-2","name":"OpenAI: GPT Audio Mini","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio","pdf"],"reference":{"provider":"kilo","input":0.6,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.6,"output":2.4,"cacheRead":null},"blendedRef":1.05,"blendedMin":1.05,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-19","lastUpdated":"2026-01-19","url":"https://llmpricing.dev/m/openai/gpt-audio-mini-2/"},{"id":"openai/gpt-chat-latest-2","name":"OpenAI: GPT Chat Latest","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":5,"output":30,"cacheRead":0.5,"official":false},"cheapest":{"provider":"kilo","input":5,"output":30,"cacheRead":0.5},"blendedRef":11.25,"blendedMin":11.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-05","lastUpdated":"2026-05-05","url":"https://llmpricing.dev/m/openai/gpt-chat-latest-2/"},{"id":"openai/gpt-3.5-turbo-0613-2","name":"OpenAI: GPT-3.5 Turbo (older v0613)","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":4095,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":1,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1,"output":2,"cacheRead":null},"blendedRef":1.25,"blendedMin":1.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-25","lastUpdated":"2024-01-25","url":"https://llmpricing.dev/m/openai/gpt-3.5-turbo-0613-2/"},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["pdf","image","text"],"reference":{"provider":"kilo","input":1.75,"output":14,"cacheRead":0.175,"official":false},"cheapest":{"provider":"kilo","input":1.75,"output":14,"cacheRead":0.175},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-10","lastUpdated":"2025-12-10","url":"https://llmpricing.dev/m/openai/gpt-5.2-chat/"},{"id":"openai/gpt-oss-safeguard-20b-3","name":"OpenAI: gpt-oss-safeguard-20b","lab":"openai","kind":"classify","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.075,"output":0.3,"cacheRead":0.0375,"official":false},"cheapest":{"provider":"kilo","input":0.075,"output":0.3,"cacheRead":0.0375},"blendedRef":0.1312,"blendedMin":0.1312,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-29","lastUpdated":"2025-10-29","url":"https://llmpricing.dev/m/openai/gpt-oss-safeguard-20b-3/"},{"id":"openai/gpt-5-image-2","name":"OpenAI: GPT-5 Image ($$$$)","lab":"openai","kind":"image","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["image","text","pdf"],"reference":{"provider":"kilo","input":10,"output":10,"cacheRead":1.25,"official":false},"cheapest":{"provider":"kilo","input":10,"output":10,"cacheRead":1.25},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-14","lastUpdated":"2025-10-14","url":"https://llmpricing.dev/m/openai/gpt-5-image-2/"},{"id":"kilo-auto/small","name":"Auto Small","lab":"kilo-auto","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.05,"output":0.4,"cacheRead":0.005,"official":false},"cheapest":{"provider":"kilo","input":0.05,"output":0.4,"cacheRead":0.005},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"1970-01-01","lastUpdated":"1970-01-01","url":"https://llmpricing.dev/m/kilo-auto/small/"},{"id":"kilo-auto/frontier","name":"Auto Frontier","lab":"kilo-auto","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":5,"output":25,"cacheRead":0.5,"official":false},"cheapest":{"provider":"kilo","input":5,"output":25,"cacheRead":0.5},"blendedRef":10,"blendedMin":10,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"1970-01-01","lastUpdated":"1970-01-01","url":"https://llmpricing.dev/m/kilo-auto/frontier/"},{"id":"kilo-auto/efficient","name":"Auto Efficient","lab":"kilo-auto","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.325,"output":1.95,"cacheRead":0.0325,"official":false},"cheapest":{"provider":"kilo","input":0.325,"output":1.95,"cacheRead":0.0325},"blendedRef":0.7313,"blendedMin":0.7313,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"1970-01-01","lastUpdated":"1970-01-01","url":"https://llmpricing.dev/m/kilo-auto/efficient/"},{"id":"kilo-auto/balanced","name":"Auto Balanced","lab":"kilo-auto","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.325,"output":1.95,"cacheRead":0.0325,"official":false},"cheapest":{"provider":"kilo","input":0.325,"output":1.95,"cacheRead":0.0325},"blendedRef":0.7313,"blendedMin":0.7313,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"1970-01-01","lastUpdated":"1970-01-01","url":"https://llmpricing.dev/m/kilo-auto/balanced/"},{"id":"kilo-auto/free","name":"Auto Free","lab":"kilo-auto","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":10000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"1970-01-01","lastUpdated":"1970-01-01","url":"https://llmpricing.dev/m/kilo-auto/free/"},{"id":"meituan/longcat-2.0-2","name":"Meituan: LongCat 2.0","lab":"meituan","kind":"text","status":"ga","openWeights":false,"context":1048756,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.75,"output":3,"cacheRead":0.015,"official":false},"cheapest":{"provider":"kilo","input":0.75,"output":3,"cacheRead":0.015},"blendedRef":1.3125,"blendedMin":1.3125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-20","lastUpdated":"2026-07-20","url":"https://llmpricing.dev/m/meituan/longcat-2.0-2/"},{"id":"nousresearch/hermes-3-llama-3.1-405b-2","name":"Nous: Hermes 3 405B Instruct","lab":"nousresearch","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":1,"output":1,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1,"output":1,"cacheRead":null},"blendedRef":1,"blendedMin":1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-16","lastUpdated":"2024-08-16","url":"https://llmpricing.dev/m/nousresearch/hermes-3-llama-3.1-405b-2/"},{"id":"nousresearch/hermes-3-llama-3.1-70b-3","name":"Nous: Hermes 3 70B Instruct","lab":"nousresearch","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.7,"output":0.7,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.7,"output":0.7,"cacheRead":null},"blendedRef":0.7,"blendedMin":0.7,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-18","lastUpdated":"2024-08-18","url":"https://llmpricing.dev/m/nousresearch/hermes-3-llama-3.1-70b-3/"},{"id":"nousresearch/hermes-4-70b-3","name":"Nous: Hermes 4 70B","lab":"nousresearch","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.13,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.13,"output":0.4,"cacheRead":null},"blendedRef":0.1975,"blendedMin":0.1975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/nousresearch/hermes-4-70b-3/"},{"id":"nousresearch/hermes-4-405b-3","name":"Nous: Hermes 4 405B","lab":"nousresearch","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":26215,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1,"output":3,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/nousresearch/hermes-4-405b-3/"},{"id":"stepfun/step-3.7-flash-free-2","name":"StepFun: Step 3.7 Flash (free)","lab":"stepfun","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-05-29","lastUpdated":"2026-05-29","url":"https://llmpricing.dev/m/stepfun/step-3.7-flash-free-2/"},{"id":"alibaba/qwen2.5-vl-72b-instruct-2","name":"Qwen: Qwen2.5 VL 72B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.8,"output":1,"cacheRead":0.4,"official":false},"cheapest":{"provider":"kilo","input":0.8,"output":1,"cacheRead":0.4},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-01","lastUpdated":"2025-02-01","url":"https://llmpricing.dev/m/alibaba/qwen2.5-vl-72b-instruct-2/"},{"id":"alibaba/qwen3.5-plus-20260420-2","name":"Qwen: Qwen3.5 Plus 2026-04-20","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":0.3,"output":1.8,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":1.8,"cacheRead":null},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-27","lastUpdated":"2026-04-27","url":"https://llmpricing.dev/m/alibaba/qwen3.5-plus-20260420-2/"},{"id":"alibaba/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":0.065,"output":0.26,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.065,"output":0.26,"cacheRead":null},"blendedRef":0.1138,"blendedMin":0.1138,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-25","lastUpdated":"2026-02-25","url":"https://llmpricing.dev/m/alibaba/qwen3.5-flash-02-23/"},{"id":"alibaba/qwen-plus-2025-07-28-thinking-2","name":"Qwen: Qwen Plus 0728 (thinking)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.26,"output":0.78,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.26,"output":0.78,"cacheRead":null},"blendedRef":0.39,"blendedMin":0.39,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-08","lastUpdated":"2025-09-08","url":"https://llmpricing.dev/m/alibaba/qwen-plus-2025-07-28-thinking-2/"},{"id":"alibaba/qwen3-vl-8b-thinking-2","name":"Qwen: Qwen3 VL 8B Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"kilo","input":0.18,"output":2.1,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.18,"output":2.1,"cacheRead":null},"blendedRef":0.66,"blendedMin":0.66,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-14","lastUpdated":"2025-10-14","url":"https://llmpricing.dev/m/alibaba/qwen3-vl-8b-thinking-2/"},{"id":"alibaba/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.1495,"output":0.598,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.1495,"output":0.598,"cacheRead":null},"blendedRef":0.2616,"blendedMin":0.2616,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-21","lastUpdated":"2025-07-21","url":"https://llmpricing.dev/m/alibaba/qwen3-235b-a22b-2507/"},{"id":"alibaba/qwen3.5-plus-02-15-2","name":"Qwen: Qwen3.5 Plus 2026-02-15","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kilo","input":0.26,"output":1.56,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.26,"output":1.56,"cacheRead":null},"blendedRef":0.585,"blendedMin":0.585,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-16","lastUpdated":"2026-02-16","url":"https://llmpricing.dev/m/alibaba/qwen3.5-plus-02-15-2/"},{"id":"alibaba/qwen3-coder-4","name":"Qwen: Qwen3 Coder 480B A35B","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.975,"output":4.875,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.975,"output":4.875,"cacheRead":null},"blendedRef":1.95,"blendedMin":1.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-23","lastUpdated":"2025-07-23","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-4/"},{"id":"alibaba/qwen3-max-thinking-2","name":"Qwen: Qwen3 Max Thinking","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.78,"output":3.9,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.78,"output":3.9,"cacheRead":null},"blendedRef":1.56,"blendedMin":1.56,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-09","lastUpdated":"2026-02-09","url":"https://llmpricing.dev/m/alibaba/qwen3-max-thinking-2/"},{"id":"alibaba/qwen-plus-2025-07-28-2","name":"Qwen: Qwen Plus 0728","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.26,"output":0.78,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.26,"output":0.78,"cacheRead":null},"blendedRef":0.39,"blendedMin":0.39,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-08","lastUpdated":"2025-09-08","url":"https://llmpricing.dev/m/alibaba/qwen-plus-2025-07-28-2/"},{"id":"alibaba/qwen3-30b-a3b-thinking-2507-2","name":"Qwen: Qwen3 30B A3B Thinking 2507","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":81920,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.2,"output":2.4,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.2,"output":2.4,"cacheRead":null},"blendedRef":0.75,"blendedMin":0.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-28","lastUpdated":"2025-08-28","url":"https://llmpricing.dev/m/alibaba/qwen3-30b-a3b-thinking-2507-2/"},{"id":"liquid/lfm-2.5-2.6b-free-2","name":"LiquidAI: LFM2.5-2.6B (free)","lab":"liquid","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/liquid/lfm-2.5-2.6b-free-2/"},{"id":"allenai/olmo-3-32b-think-2","name":"AllenAI: Olmo 3 32B Think","lab":"allenai","kind":"text","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.15,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.15,"output":0.5,"cacheRead":null},"blendedRef":0.2375,"blendedMin":0.2375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-21","lastUpdated":"2025-11-21","url":"https://llmpricing.dev/m/allenai/olmo-3-32b-think-2/"},{"id":"perplexity/sonar-pro-search-2","name":"Perplexity: Sonar Pro Search","lab":"perplexity","kind":"text","status":"ga","openWeights":false,"context":200000,"contextRange":null,"outputLimit":8000,"capabilities":{"reasoning":true,"toolCall":false,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-30","lastUpdated":"2025-10-30","url":"https://llmpricing.dev/m/perplexity/sonar-pro-search-2/"},{"id":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","lab":"thedrummer","kind":"text","status":"ga","openWeights":false,"context":65536,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.25,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.25,"output":0.5,"cacheRead":null},"blendedRef":0.3125,"blendedMin":0.3125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-30","lastUpdated":"2024-09-30","url":"https://llmpricing.dev/m/thedrummer/rocinante-12b/"},{"id":"thedrummer/unslopnemo-12b-2","name":"TheDrummer: UnslopNemo 12B","lab":"thedrummer","kind":"text","status":"ga","openWeights":false,"context":1024000,"contextRange":null,"outputLimit":1024000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.4,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.4,"output":0.4,"cacheRead":null},"blendedRef":0.4,"blendedMin":0.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-08","lastUpdated":"2024-11-08","url":"https://llmpricing.dev/m/thedrummer/unslopnemo-12b-2/"},{"id":"anthropic/claude-opus-4.8","name":"Stealth: Claude Opus 4.8 (20% off)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":4,"output":20,"cacheRead":0.4,"official":false},"cheapest":{"provider":"kilo","input":4,"output":20,"cacheRead":0.4},"blendedRef":8,"blendedMin":8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.8/"},{"id":"anthropic/claude-sonnet-4.6","name":"Stealth: Claude Sonnet 4.6 (20% off)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":2.4,"output":12,"cacheRead":0.24,"official":false},"cheapest":{"provider":"kilo","input":2.4,"output":12,"cacheRead":0.24},"blendedRef":4.8,"blendedMin":4.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/anthropic/claude-sonnet-4.6/"},{"id":"anthropic/claude-opus-4.7-2","name":"Stealth: Claude Opus 4.7 (20% off)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":4,"output":20,"cacheRead":0.4,"official":false},"cheapest":{"provider":"kilo","input":4,"output":20,"cacheRead":0.4},"blendedRef":8,"blendedMin":8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.7-2/"},{"id":"anthropic/claude-opus-4.6-2","name":"Stealth: Claude Opus 4.6 (20% off)","lab":"anthropic","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":4,"output":20,"cacheRead":0.4,"official":false},"cheapest":{"provider":"kilo","input":4,"output":20,"cacheRead":0.4},"blendedRef":8,"blendedMin":8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/anthropic/claude-opus-4.6-2/"},{"id":"alibaba/qwen3.6-plus-3","name":"Stealth: Qwen3.6 Plus (50% off)","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.25,"output":1.5,"cacheRead":0.025,"official":false},"cheapest":{"provider":"kilo","input":0.25,"output":1.5,"cacheRead":0.025},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-26","lastUpdated":"2025-08-26","url":"https://llmpricing.dev/m/alibaba/qwen3.6-plus-3/"},{"id":"writer/palmyra-x5-2","name":"Writer: Palmyra X5","lab":"writer","kind":"text","status":"ga","openWeights":false,"context":1040000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.6,"output":6,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.6,"output":6,"cacheRead":null},"blendedRef":1.95,"blendedMin":1.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-21","lastUpdated":"2026-01-21","url":"https://llmpricing.dev/m/writer/palmyra-x5-2/"},{"id":"inclusionai/ring-2.6-1t-3","name":"inclusionAI: Ring-2.6-1T (retires Aug 24)","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.3,"output":2.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":2.5,"cacheRead":0.06},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-08","lastUpdated":"2026-05-08","url":"https://llmpricing.dev/m/inclusionai/ring-2.6-1t-3/"},{"id":"inclusionai/ling-2.6-1t-2","name":"inclusionAI: Ling-2.6-1T (retires Aug 24)","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.3,"output":2.5,"cacheRead":0.06,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":2.5,"cacheRead":0.06},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-23","lastUpdated":"2026-04-23","url":"https://llmpricing.dev/m/inclusionai/ling-2.6-1t-2/"},{"id":"inclusionai/ling-2.6-flash-2","name":"inclusionAI: Ling-2.6-flash (retires Aug 24)","lab":"inclusionai","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.1,"output":0.3,"cacheRead":0.02,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.3,"cacheRead":0.02},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-21","lastUpdated":"2026-04-21","url":"https://llmpricing.dev/m/inclusionai/ling-2.6-flash-2/"},{"id":"meta/llama-3.2-3b-instruct-3","name":"Meta: Llama 3.2 3B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.05,"output":0.33,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.05,"output":0.33,"cacheRead":null},"blendedRef":0.12,"blendedMin":0.12,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-3b-instruct-3/"},{"id":"meta/llama-3.2-1b-instruct-2","name":"Meta: Llama 3.2 1B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":60000,"contextRange":null,"outputLimit":60000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.027,"output":0.201,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.027,"output":0.201,"cacheRead":null},"blendedRef":0.0705,"blendedMin":0.0705,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-1b-instruct-2/"},{"id":"meta/llama-3.1-70b-instruct-3","name":"Meta: Llama 3.1 70B Instruct","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.4,"output":0.4,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.4,"output":0.4,"cacheRead":null},"blendedRef":0.4,"blendedMin":0.4,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-70b-instruct-3/"},{"id":"meta/llama-4-maverick-3","name":"Meta: Llama 4 Maverick","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.2,"output":0.696,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.2,"output":0.696,"cacheRead":null},"blendedRef":0.324,"blendedMin":0.324,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-maverick-3/"},{"id":"meta/llama-4-scout-3","name":"Meta: Llama 4 Scout","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":327680,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.1,"output":0.3,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.3,"cacheRead":null},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-05","lastUpdated":"2025-04-05","url":"https://llmpricing.dev/m/meta/llama-4-scout-3/"},{"id":"mistral/ministral-8b-2512-4","name":"Mistral: Ministral 3 8B 2512","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.15,"output":0.15,"cacheRead":0.015,"official":false},"cheapest":{"provider":"kilo","input":0.15,"output":0.15,"cacheRead":0.015},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-8b-2512-4/"},{"id":"mistral/mistral-medium-3.1-2","name":"Mistral: Mistral Medium 3.1","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":26215,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":0.4,"output":2,"cacheRead":0.04,"official":false},"cheapest":{"provider":"kilo","input":0.4,"output":2,"cacheRead":0.04},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-13","lastUpdated":"2025-08-13","url":"https://llmpricing.dev/m/mistral/mistral-medium-3.1-2/"},{"id":"mistral/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":1.5,"output":7.5,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1.5,"output":7.5,"cacheRead":null},"blendedRef":3,"blendedMin":3,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/mistral/mistral-medium-3-5/"},{"id":"mistral/ministral-8b","name":"Mistral: Ministral 8B","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.11,"output":0.11,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.11,"output":0.11,"cacheRead":null},"blendedRef":0.11,"blendedMin":0.11,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-17","lastUpdated":"2024-10-17","url":"https://llmpricing.dev/m/mistral/ministral-8b/"},{"id":"mistral/mistral-small-3.2-24b-instruct-2","name":"Mistral: Mistral Small 3.2 24B","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"kilo","input":0.09375,"output":0.25,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.09375,"output":0.25,"cacheRead":null},"blendedRef":0.1328,"blendedMin":0.1328,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-20","lastUpdated":"2025-06-20","url":"https://llmpricing.dev/m/mistral/mistral-small-3.2-24b-instruct-2/"},{"id":"mistral/mistral-small-24b-instruct-2501-2","name":"Mistral: Mistral Small 3","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.05,"output":0.08,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.05,"output":0.08,"cacheRead":null},"blendedRef":0.0575,"blendedMin":0.0575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-30","lastUpdated":"2025-01-30","url":"https://llmpricing.dev/m/mistral/mistral-small-24b-instruct-2501-2/"},{"id":"mistral/voxtral-small-24b-2507-3","name":"Mistral: Voxtral Small 24B 2507","lab":"mistral","kind":"audio","status":"ga","openWeights":false,"context":32000,"contextRange":null,"outputLimit":6400,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","audio","pdf"],"reference":{"provider":"kilo","input":0.1,"output":0.3,"cacheRead":0.01,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.3,"cacheRead":0.01},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-30","lastUpdated":"2025-10-30","url":"https://llmpricing.dev/m/mistral/voxtral-small-24b-2507-3/"},{"id":"mistral/ministral-3b-2512-4","name":"Mistral: Ministral 3 3B 2512","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.1,"output":0.1,"cacheRead":0.01,"official":false},"cheapest":{"provider":"kilo","input":0.1,"output":0.1,"cacheRead":0.01},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-3b-2512-4/"},{"id":"mistral/mistral-medium-3","name":"Mistral: Mistral Medium 3","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":26215,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"kilo","input":0.4,"output":2,"cacheRead":0.04,"official":false},"cheapest":{"provider":"kilo","input":0.4,"output":2,"cacheRead":0.04},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-05-07","lastUpdated":"2025-05-07","url":"https://llmpricing.dev/m/mistral/mistral-medium-3/"},{"id":"mistral/ministral-14b-2512-4","name":"Mistral: Ministral 3 14B 2512","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":52429,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.2,"output":0.2,"cacheRead":0.02,"official":false},"cheapest":{"provider":"kilo","input":0.2,"output":0.2,"cacheRead":0.02},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-02","lastUpdated":"2025-12-02","url":"https://llmpricing.dev/m/mistral/ministral-14b-2512-4/"},{"id":"mistral/codestral-2508-4","name":"Mistral: Codestral 2508","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":51200,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","pdf"],"reference":{"provider":"kilo","input":0.3,"output":0.9,"cacheRead":0.03,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":0.9,"cacheRead":0.03},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-08-01","lastUpdated":"2025-08-01","url":"https://llmpricing.dev/m/mistral/codestral-2508-4/"},{"id":"mistral/mistral-small-3.1-24b-instruct-2","name":"Mistral: Mistral Small 3.1 24B","lab":"mistral","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.351,"output":0.555,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.351,"output":0.555,"cacheRead":null},"blendedRef":0.402,"blendedMin":0.402,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-17","lastUpdated":"2025-03-17","url":"https://llmpricing.dev/m/mistral/mistral-small-3.1-24b-instruct-2/"},{"id":"morph/morph-v3-large-2","name":"Morph: Morph V3 Large","lab":"morph","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.9,"output":1.9,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.9,"output":1.9,"cacheRead":null},"blendedRef":1.15,"blendedMin":1.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-07","lastUpdated":"2025-07-07","url":"https://llmpricing.dev/m/morph/morph-v3-large-2/"},{"id":"morph/morph-v3-fast-2","name":"Morph: Morph V3 Fast","lab":"morph","kind":"text","status":"ga","openWeights":false,"context":81920,"contextRange":null,"outputLimit":38000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.8,"output":1.2,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.8,"output":1.2,"cacheRead":null},"blendedRef":0.9,"blendedMin":0.9,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-07","lastUpdated":"2025-07-07","url":"https://llmpricing.dev/m/morph/morph-v3-fast-2/"},{"id":"amazon/nova-premier-v1-2","name":"Amazon: Nova Premier 1.0","lab":"amazon","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":32000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":2.5,"output":12.5,"cacheRead":0.625,"official":false},"cheapest":{"provider":"kilo","input":2.5,"output":12.5,"cacheRead":0.625},"blendedRef":5,"blendedMin":5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-31","lastUpdated":"2025-10-31","url":"https://llmpricing.dev/m/amazon/nova-premier-v1-2/"},{"id":"zhipuai/glm-latest-2","name":"Z.ai: GLM Latest","lab":"zhipuai","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":1.4,"output":4.4,"cacheRead":0.26,"official":false},"cheapest":{"provider":"kilo","input":1.4,"output":4.4,"cacheRead":0.26},"blendedRef":2.15,"blendedMin":2.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-19","lastUpdated":"2026-08-19","url":"https://llmpricing.dev/m/zhipuai/glm-latest-2/"},{"id":"nex-agi/nex-n2-mini-2","name":"Nex AGI: Nex-N2-Mini","lab":"nex-agi","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.025,"output":0.1,"cacheRead":0.0025,"official":false},"cheapest":{"provider":"kilo","input":0.025,"output":0.1,"cacheRead":0.0025},"blendedRef":0.0438,"blendedMin":0.0438,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-24","lastUpdated":"2026-06-24","url":"https://llmpricing.dev/m/nex-agi/nex-n2-mini-2/"},{"id":"nex-agi/nex-n2-pro-2","name":"Nex AGI: Nex-N2-Pro","lab":"nex-agi","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.25,"output":1,"cacheRead":0.025,"official":false},"cheapest":{"provider":"kilo","input":0.25,"output":1,"cacheRead":0.025},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-08","lastUpdated":"2026-06-08","url":"https://llmpricing.dev/m/nex-agi/nex-n2-pro-2/"},{"id":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.15,"output":0.6,"cacheRead":0.015,"official":false},"cheapest":{"provider":"kilo","input":0.15,"output":0.6,"cacheRead":0.015},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-01-27","url":"https://llmpricing.dev/m/upstage/solar-pro-3/"},{"id":"upstage/solar-pro4-2","name":"Upstage: Solar Pro 4","lab":"upstage","kind":"text","status":"ga","openWeights":false,"context":524288,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-10","lastUpdated":"2026-08-10","url":"https://llmpricing.dev/m/upstage/solar-pro4-2/"},{"id":"baidu/ernie-4.5-vl-424b-a47b-3","name":"Baidu: ERNIE 4.5 VL 424B A47B ","lab":"baidu","kind":"text","status":"ga","openWeights":false,"context":123000,"contextRange":null,"outputLimit":16000,"capabilities":{"reasoning":true,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["image","text"],"reference":{"provider":"kilo","input":0.42,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.42,"output":1.25,"cacheRead":null},"blendedRef":0.6275,"blendedMin":0.6275,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/baidu/ernie-4.5-vl-424b-a47b-3/"},{"id":"mancer/weaver-2","name":"Mancer: Weaver (alpha)","lab":"mancer","kind":"text","status":"ga","openWeights":false,"context":8000,"contextRange":null,"outputLimit":6000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.5,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.5,"output":0.75,"cacheRead":null},"blendedRef":0.5625,"blendedMin":0.5625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2023-08-02","lastUpdated":"2023-08-02","url":"https://llmpricing.dev/m/mancer/weaver-2/"},{"id":"meta/l3.1-euryale-70b-2","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.85,"output":0.85,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.85,"output":0.85,"cacheRead":null},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-28","lastUpdated":"2024-08-28","url":"https://llmpricing.dev/m/meta/l3.1-euryale-70b-2/"},{"id":"meta/l3.3-euryale-70b-2","name":"Sao10K: Llama 3.3 Euryale 70B","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.65,"output":0.75,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.65,"output":0.75,"cacheRead":null},"blendedRef":0.675,"blendedMin":0.675,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-18","lastUpdated":"2024-12-18","url":"https://llmpricing.dev/m/meta/l3.3-euryale-70b-2/"},{"id":"meta/l3-lunaris-8b-2","name":"Sao10K: Llama 3 8B Lunaris","lab":"meta","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.04,"output":0.05,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.04,"output":0.05,"cacheRead":null},"blendedRef":0.0425,"blendedMin":0.0425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-08-13","lastUpdated":"2024-08-13","url":"https://llmpricing.dev/m/meta/l3-lunaris-8b-2/"},{"id":"kwaipilot/kat-coder-pro-v2.5-2","name":"Kwaipilot: KAT-Coder-Pro V2.5","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.74,"output":2.96,"cacheRead":0.15,"official":false},"cheapest":{"provider":"kilo","input":0.74,"output":2.96,"cacheRead":0.15},"blendedRef":1.295,"blendedMin":1.295,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-10","lastUpdated":"2026-07-10","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-pro-v2.5-2/"},{"id":"kwaipilot/kat-coder-air-v2.5-2","name":"Kwaipilot: KAT-Coder-Air V2.5","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.15,"output":0.6,"cacheRead":0.03,"official":false},"cheapest":{"provider":"kilo","input":0.15,"output":0.6,"cacheRead":0.03},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-07-10","lastUpdated":"2026-07-10","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-air-v2.5-2/"},{"id":"kwaipilot/kat-coder-pro-v2-2","name":"Kwaipilot: KAT-Coder-Pro V2","lab":"kwaipilot","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":80000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"kilo","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-03-27","lastUpdated":"2026-03-27","url":"https://llmpricing.dev/m/kwaipilot/kat-coder-pro-v2-2/"},{"id":"ibm-granite/granite-4.0-h-micro-2","name":"IBM: Granite 4.0 Micro","lab":"ibm-granite","kind":"text","status":"ga","openWeights":false,"context":131000,"contextRange":null,"outputLimit":131000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.017,"output":0.112,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.017,"output":0.112,"cacheRead":null},"blendedRef":0.0408,"blendedMin":0.0408,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-10-20","lastUpdated":"2025-10-20","url":"https://llmpricing.dev/m/ibm-granite/granite-4.0-h-micro-2/"},{"id":"ibm-granite/granite-4.1-8b-2","name":"IBM: Granite 4.1 8B","lab":"ibm-granite","kind":"text","status":"ga","openWeights":false,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.05,"output":0.1,"cacheRead":0.05,"official":false},"cheapest":{"provider":"kilo","input":0.05,"output":0.1,"cacheRead":0.05},"blendedRef":0.0625,"blendedMin":0.0625,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/ibm-granite/granite-4.1-8b-2/"},{"id":"dots-studio/dots-3-note-preview-free-2","name":"Dots Studio: Dots3-Note Preview (free)","lab":"dots-studio","kind":"text","status":"ga","openWeights":false,"context":512000,"contextRange":null,"outputLimit":512000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0,"output":0,"cacheRead":null,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-08-14","lastUpdated":"2026-08-14","url":"https://llmpricing.dev/m/dots-studio/dots-3-note-preview-free-2/"},{"id":"minimax/minimax-01-2","name":"MiniMax: MiniMax-01","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":1000192,"contextRange":null,"outputLimit":1000192,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"kilo","input":0.2,"output":1.1,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.2,"output":1.1,"cacheRead":null},"blendedRef":0.425,"blendedMin":0.425,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-01-15","lastUpdated":"2025-01-15","url":"https://llmpricing.dev/m/minimax/minimax-01-2/"},{"id":"minimax/minimax-m1-2","name":"MiniMax: MiniMax M1","lab":"minimax","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":40000,"capabilities":{"reasoning":true,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.4,"output":2.2,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.4,"output":2.2,"cacheRead":null},"blendedRef":0.85,"blendedMin":0.85,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-17","lastUpdated":"2025-06-17","url":"https://llmpricing.dev/m/minimax/minimax-m1-2/"},{"id":"relace/relace-search-2","name":"Relace: Relace Search","lab":"relace","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":1,"output":3,"cacheRead":null},"blendedRef":1.5,"blendedMin":1.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-12-08","lastUpdated":"2025-12-08","url":"https://llmpricing.dev/m/relace/relace-search-2/"},{"id":"relace/relace-apply-3-2","name":"Relace: Relace Apply 3","lab":"relace","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":false,"structured":false,"attachment":false},"inputModalities":["text"],"reference":{"provider":"kilo","input":0.85,"output":1.25,"cacheRead":null,"official":false},"cheapest":{"provider":"kilo","input":0.85,"output":1.25,"cacheRead":null},"blendedRef":0.95,"blendedMin":0.95,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-26","lastUpdated":"2025-09-26","url":"https://llmpricing.dev/m/relace/relace-apply-3-2/"},{"id":"google/gemma-3-4b-pt","name":"Gemma 3 4B (Pretrained)","lab":"google","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-02-28","lastUpdated":"2025-02-28","url":"https://llmpricing.dev/m/google/gemma-3-4b-pt/"},{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B-A4B IT","lab":"google","kind":"text","status":"ga","openWeights":false,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.5,"output":0.5,"cacheRead":0.5,"official":false},"cheapest":{"provider":"pioneer","input":0.5,"output":0.5,"cacheRead":0.5},"blendedRef":0.5,"blendedMin":0.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-31","lastUpdated":"2026-05-31","url":"https://llmpricing.dev/m/google/diffusiongemma-26b-a4b-it/"},{"id":"google/gemma-4-12b-it-2","name":"Gemma 4 12B IT","lab":"google","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.25,"output":0.25,"cacheRead":0.25,"official":false},"cheapest":{"provider":"pioneer","input":0.25,"output":0.25,"cacheRead":0.25},"blendedRef":0.25,"blendedMin":0.25,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-05-31","lastUpdated":"2026-05-31","url":"https://llmpricing.dev/m/google/gemma-4-12b-it-2/"},{"id":"google/gemma-4-E2B-it","name":"Gemma 4 E2B IT","lab":"google","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","audio"],"reference":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1,"official":false},"cheapest":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-04-02","url":"https://llmpricing.dev/m/google/gemma-4-E2B-it/"},{"id":"alibaba/qwen2.5-coder-0.5b","name":"Qwen2.5-Coder-0.5B","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1,"official":false},"cheapest":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-11-12","lastUpdated":"2024-11-12","url":"https://llmpricing.dev/m/alibaba/qwen2.5-coder-0.5b/"},{"id":"alibaba/qwen3-1.7b-base","name":"Qwen3 1.7B Base","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1,"official":false},"cheapest":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-31","lastUpdated":"2025-03-31","url":"https://llmpricing.dev/m/alibaba/qwen3-1.7b-base/"},{"id":"alibaba/qwen3-4b-base","name":"Qwen3 4B Base","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-03-31","lastUpdated":"2025-03-31","url":"https://llmpricing.dev/m/alibaba/qwen3-4b-base/"},{"id":"alibaba/qwen3-4b-instruct-2507","name":"Qwen3 4B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.2,"output":0.2,"cacheRead":0.2,"official":false},"cheapest":{"provider":"pioneer","input":0.2,"output":0.2,"cacheRead":0.2},"blendedRef":0.2,"blendedMin":0.2,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-31","lastUpdated":"2025-07-31","url":"https://llmpricing.dev/m/alibaba/qwen3-4b-instruct-2507/"},{"id":"fastino/gliner2-privacy-filter-pii-multi","name":"GLiNER2 Privacy Filter PII (Multi)","lab":"fastino","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/fastino/gliner2-privacy-filter-pii-multi/"},{"id":"fastino/gliner2-multi-v1","name":"GLiNER2 Multi","lab":"fastino","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-30","lastUpdated":"2025-11-30","url":"https://llmpricing.dev/m/fastino/gliner2-multi-v1/"},{"id":"fastino/gliner2-large-v1","name":"GLiNER2 Large","lab":"fastino","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/fastino/gliner2-large-v1/"},{"id":"fastino/gliguard-llmguardrails-300m","name":"GLiGuard LLM Guardrails 300M","lab":"fastino","kind":"classify","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-30","lastUpdated":"2026-04-30","url":"https://llmpricing.dev/m/fastino/gliguard-llmguardrails-300m/"},{"id":"fastino/gliner2-base-v1","name":"GLiNER2 Base","lab":"fastino","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/fastino/gliner2-base-v1/"},{"id":"fastino/gliner2-multi-large-v1","name":"GLiNER2 Multi Large","lab":"fastino","kind":"text","status":"ga","openWeights":false,"context":8192,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-11-30","lastUpdated":"2025-11-30","url":"https://llmpricing.dev/m/fastino/gliner2-multi-large-v1/"},{"id":"meta/llama-3.2-1b","name":"Llama-3.2-1B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1,"official":false},"cheapest":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1},"blendedRef":0.1,"blendedMin":0.1,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-1b/"},{"id":"meta/llama-3.2-3b","name":"Llama-3.2-3B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":[128000,131072],"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"pioneer","input":0.1,"output":0.1,"cacheRead":0.1},"blendedRef":0.2625,"blendedMin":0.1,"blendedTrusted":null,"spread":1.5,"hostCount":2,"pricedHostCount":2,"aa":null,"usage":null,"releaseDate":"2024-09-25","lastUpdated":"2024-09-25","url":"https://llmpricing.dev/m/meta/llama-3.2-3b/"},{"id":"mistral/ministral-8b-instruct-2410","name":"Ministral 8B Instruct","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-10-16","lastUpdated":"2024-10-16","url":"https://llmpricing.dev/m/mistral/ministral-8b-instruct-2410/"},{"id":"mistral/codestral-22b-v0.1","name":"Codestral-22B-v0.1","lab":"mistral","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4000,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.3,"output":0.9,"cacheRead":0.3,"official":false},"cheapest":{"provider":"pioneer","input":0.3,"output":0.9,"cacheRead":0.3},"blendedRef":0.45,"blendedMin":0.45,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-05-29","lastUpdated":"2024-05-29","url":"https://llmpricing.dev/m/mistral/codestral-22b-v0.1/"},{"id":"huggingfacetb/smollm3-3b-base","name":"SmolLM3 3B Base","lab":"huggingfacetb","kind":"text","status":"ga","openWeights":false,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15,"official":false},"cheapest":{"provider":"pioneer","input":0.15,"output":0.15,"cacheRead":0.15},"blendedRef":0.15,"blendedMin":0.15,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-06-30","lastUpdated":"2025-06-30","url":"https://llmpricing.dev/m/huggingfacetb/smollm3-3b-base/"},{"id":"pioneer/auto","name":"Pioneer Auto","lab":"pioneer","kind":"text","status":"ga","openWeights":false,"context":1048576,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":null,"cheapest":null,"blendedRef":null,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2025-06-29","url":"https://llmpricing.dev/m/pioneer/auto/"},{"id":"deepseek/deepseek-v4-flash-0731-fast","name":"DeepSeek V4 Flash 0731 Fast","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.35,"output":0.7,"cacheRead":0.0875,"official":false},"cheapest":{"provider":"venice","input":0.35,"output":0.7,"cacheRead":0.0875},"blendedRef":0.4375,"blendedMin":0.4375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-09","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-0731-fast/"},{"id":"minimax/minimax-m3-preview","name":"MiniMax M3 Preview","lab":"minimax","kind":"text","status":"ga","openWeights":true,"context":524288,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"venice","input":0.3,"output":1.2,"cacheRead":0.06,"official":false},"cheapest":{"provider":"venice","input":0.3,"output":1.2,"cacheRead":0.06},"blendedRef":0.525,"blendedMin":0.525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-13","url":"https://llmpricing.dev/m/minimax/minimax-m3-preview/"},{"id":"deepseek/deepseek-v4-flash-14","name":"DeepSeek V4 Flash 0423","lab":"deepseek","kind":"text","status":"ga","openWeights":true,"context":1000000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.138,"output":0.275,"cacheRead":0.028,"official":false},"cheapest":{"provider":"venice","input":0.138,"output":0.275,"cacheRead":0.028},"blendedRef":0.1723,"blendedMin":0.1723,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":{"rank":4,"tokens":25850514412772,"share":0.09687628281733425},"releaseDate":"2026-04-24","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/deepseek/deepseek-v4-flash-14/"},{"id":"misc/hermes-3-llama-3.1-405b","name":"Hermes 3 Llama 3.1 405b","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":false,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":1.1,"output":3,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":1.1,"output":3,"cacheRead":null},"blendedRef":1.575,"blendedMin":1.575,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-09-25","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/misc/hermes-3-llama-3.1-405b/"},{"id":"misc/venice-uncensored-role-play","name":"Venice Role Play Uncensored","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"venice","input":0.5,"output":2,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":0.5,"output":2,"cacheRead":null},"blendedRef":0.875,"blendedMin":0.875,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-20","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/misc/venice-uncensored-role-play/"},{"id":"alibaba/qwen3-next-80b","name":"Qwen 3 Next 80b","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":16384,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.35,"output":1.9,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":0.35,"output":1.9,"cacheRead":null},"blendedRef":0.7375,"blendedMin":0.7375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-29","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/alibaba/qwen3-next-80b/"},{"id":"zhipuai/olafangensan-glm-4.7-flash-heretic","name":"GLM 4.7 Flash Heretic","lab":"zhipuai","kind":"text","status":"ga","openWeights":true,"context":200000,"contextRange":null,"outputLimit":24000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.07,"output":0.4,"cacheRead":0.035,"official":false},"cheapest":{"provider":"venice","input":0.07,"output":0.4,"cacheRead":0.035},"blendedRef":0.1525,"blendedMin":0.1525,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-04","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/zhipuai/olafangensan-glm-4.7-flash-heretic/"},{"id":"misc/venice-uncensored-1-2","name":"Venice Uncensored 1.2","lab":"misc","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"venice","input":0.2,"output":0.9,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":0.2,"output":0.9,"cacheRead":null},"blendedRef":0.375,"blendedMin":0.375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-01","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/misc/venice-uncensored-1-2/"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct-turbo-2","name":"Qwen 3 Coder 480B Turbo","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":0.35,"output":1.5,"cacheRead":0.04,"official":false},"cheapest":{"provider":"venice","input":0.35,"output":1.5,"cacheRead":0.04},"blendedRef":0.6375,"blendedMin":0.6375,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-01-27","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/alibaba/qwen3-coder-480b-a35b-instruct-turbo-2/"},{"id":"google/google-gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"venice","input":0.13,"output":0.4,"cacheRead":0.05,"official":false},"cheapest":{"provider":"venice","input":0.13,"output":0.4,"cacheRead":0.05},"blendedRef":0.1975,"blendedMin":0.1975,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-02","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/google/google-gemma-4-26b-a4b-it/"},{"id":"alibaba/qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"venice","input":2.5,"output":7.5,"cacheRead":0.3125,"official":false},"cheapest":{"provider":"venice","input":2.5,"output":7.5,"cacheRead":0.3125},"blendedRef":3.75,"blendedMin":3.75,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-08-12","lastUpdated":"2026-08-13","url":"https://llmpricing.dev/m/alibaba/qwen-3-8-2-4t-a95b/"},{"id":"google/gemma-4-uncensored","name":"Gemma 4 Uncensored","lab":"google","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"venice","input":0.1625,"output":0.5,"cacheRead":null,"official":false},"cheapest":{"provider":"venice","input":0.1625,"output":0.5,"cacheRead":null},"blendedRef":0.2469,"blendedMin":0.2469,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-13","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/google/gemma-4-uncensored/"},{"id":"google/google-gemma-4-31b-it","name":"Google Gemma 4 31B Instruct","lab":"google","kind":"text","status":"ga","openWeights":true,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"venice","input":0.12,"output":0.36,"cacheRead":0.09,"official":false},"cheapest":{"provider":"venice","input":0.12,"output":0.36,"cacheRead":0.09},"blendedRef":0.18,"blendedMin":0.18,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-03","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/google/google-gemma-4-31b-it/"},{"id":"alibaba/qwen-3-6-plus","name":"Qwen 3.6 Plus Uncensored","lab":"alibaba","kind":"text","status":"ga","openWeights":false,"context":1000000,"contextRange":null,"outputLimit":65536,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"venice","input":0.625,"output":3.75,"cacheRead":0.0625,"official":false},"cheapest":{"provider":"venice","input":0.625,"output":3.75,"cacheRead":0.0625},"blendedRef":1.4063,"blendedMin":1.4063,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-06","lastUpdated":"2026-06-11","url":"https://llmpricing.dev/m/alibaba/qwen-3-6-plus/"},{"id":"moonshotai/kimi-k2p7-code-fast","name":"Kimi K2.7 Code Fast","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"fireworks-ai","input":1.9,"output":8,"cacheRead":0.38,"official":false},"cheapest":{"provider":"fireworks-ai","input":1.9,"output":8,"cacheRead":0.38},"blendedRef":3.425,"blendedMin":3.425,"blendedTrusted":3.425,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-16","url":"https://llmpricing.dev/m/moonshotai/kimi-k2p7-code-fast/"},{"id":"moonshotai/kimi-k2p6-turbo","name":"Kimi K2.6 Turbo","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262000,"contextRange":null,"outputLimit":262000,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"fireworks-ai","input":2,"output":8,"cacheRead":0.3,"official":false},"cheapest":{"provider":"fireworks-ai","input":2,"output":8,"cacheRead":0.3},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":3.5,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-04-17","lastUpdated":"2026-04-17","url":"https://llmpricing.dev/m/moonshotai/kimi-k2p6-turbo/"},{"id":"nvidia/nvidia-nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":262144,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.1,"output":0.25,"cacheRead":0.05,"official":false},"cheapest":{"provider":"wandb","input":0.1,"output":0.25,"cacheRead":0.05},"blendedRef":0.1375,"blendedMin":0.1375,"blendedTrusted":0.1375,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":23.6,"coding":26.8,"agentic":13.8,"speed":302,"ttft":1.16,"taskCost":0.0764},"usage":null,"releaseDate":"2026-08-11","lastUpdated":"2026-08-11","url":"https://llmpricing.dev/m/nvidia/nvidia-nemotron-3.5-lightning-30b-a3b/"},{"id":"jetbrains/mellum2-12b-a2.5b-instruct","name":"Mellum2 12B A2.5B","lab":"jetbrains","kind":"text","status":"ga","openWeights":true,"context":131072,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.05,"output":0.1,"cacheRead":0.05,"official":false},"cheapest":{"provider":"wandb","input":0.05,"output":0.1,"cacheRead":0.05},"blendedRef":0.0625,"blendedMin":0.0625,"blendedTrusted":0.0625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-06-01","lastUpdated":"2026-06-01","url":"https://llmpricing.dev/m/jetbrains/mellum2-12b-a2.5b-instruct/"},{"id":"meta/llama-3.1-70b-instruct-4","name":"Llama 3.1 70B","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.8,"output":0.8,"cacheRead":0.8,"official":false},"cheapest":{"provider":"wandb","input":0.8,"output":0.8,"cacheRead":0.8},"blendedRef":0.8,"blendedMin":0.8,"blendedTrusted":0.8,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/llama-3.1-70b-instruct-4/"},{"id":"alibaba/qwen3-14b-instruct","name":"Qwen3 14B Instruct","lab":"alibaba","kind":"text","status":"ga","openWeights":true,"context":32768,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text"],"reference":{"provider":"wandb","input":0.05,"output":0.22,"cacheRead":0.05,"official":false},"cheapest":{"provider":"wandb","input":0.05,"output":0.22,"cacheRead":0.05},"blendedRef":0.0925,"blendedMin":0.0925,"blendedTrusted":0.0925,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-04-29","lastUpdated":"2025-04-29","url":"https://llmpricing.dev/m/alibaba/qwen3-14b-instruct/"},{"id":"moonshotai/k3-256k","name":"Kimi K3-256K","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":false},"inputModalities":["text","image"],"reference":{"provider":"kimi-for-coding","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-07-16","lastUpdated":"2026-07-16","url":"https://llmpricing.dev/m/moonshotai/k3-256k/"},{"id":"moonshotai/kimi-for-coding-highspeed","name":"Kimi For Coding HighSpeed","lab":"moonshotai","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","video"],"reference":{"provider":"kimi-for-coding","input":0,"output":0,"cacheRead":0,"official":false},"cheapest":null,"blendedRef":0,"blendedMin":null,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":0,"aa":null,"usage":null,"releaseDate":"2026-06-12","lastUpdated":"2026-06-12","url":"https://llmpricing.dev/m/moonshotai/kimi-for-coding-highspeed/"},{"id":"openai/gpt-5.3-codex-xhigh","name":"GPT-5.3 Codex XHigh","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":400000,"contextRange":null,"outputLimit":128000,"capabilities":{"reasoning":true,"toolCall":true,"structured":true,"attachment":true},"inputModalities":["text","image","pdf"],"reference":{"provider":"abacus","input":1.75,"output":14,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":1.75,"output":14,"cacheRead":null},"blendedRef":4.8125,"blendedMin":4.8125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2026-02-05","lastUpdated":"2026-02-05","url":"https://llmpricing.dev/m/openai/gpt-5.3-codex-xhigh/"},{"id":"openai/route-llm","name":"RouteLLM","lab":"openai","kind":"text","status":"ga","openWeights":false,"context":128000,"contextRange":null,"outputLimit":64000,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":true},"inputModalities":["text","image"],"reference":{"provider":"abacus","input":3,"output":15,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":3,"output":15,"cacheRead":null},"blendedRef":6,"blendedMin":6,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-01-01","lastUpdated":"2026-07-10","url":"https://llmpricing.dev/m/openai/route-llm/"},{"id":"meta/llama-3.3-70b-versatile-2","name":"Llama 3.3 70B Versatile","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":32768,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abacus","input":0.59,"output":0.79,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":0.59,"output":0.79,"cacheRead":null},"blendedRef":0.64,"blendedMin":0.64,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-12-06","lastUpdated":"2024-12-06","url":"https://llmpricing.dev/m/meta/llama-3.3-70b-versatile-2/"},{"id":"moonshotai/kimi-k2-turbo-preview-2","name":"Kimi K2 Turbo Preview","lab":"moonshotai","kind":"text","status":"ga","openWeights":false,"context":256000,"contextRange":null,"outputLimit":8192,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abacus","input":0.15,"output":8,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":0.15,"output":8,"cacheRead":null},"blendedRef":2.1125,"blendedMin":2.1125,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2025-07-08","lastUpdated":"2025-07-08","url":"https://llmpricing.dev/m/moonshotai/kimi-k2-turbo-preview-2/"},{"id":"meta/meta-llama-3.1-405b-instruct-turbo","name":"Llama 3.1 405B Instruct Turbo","lab":"meta","kind":"text","status":"ga","openWeights":true,"context":128000,"contextRange":null,"outputLimit":4096,"capabilities":{"reasoning":false,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"abacus","input":3.5,"output":3.5,"cacheRead":null,"official":false},"cheapest":{"provider":"abacus","input":3.5,"output":3.5,"cacheRead":null},"blendedRef":3.5,"blendedMin":3.5,"blendedTrusted":null,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":null,"usage":null,"releaseDate":"2024-07-23","lastUpdated":"2024-07-23","url":"https://llmpricing.dev/m/meta/meta-llama-3.1-405b-instruct-turbo/"},{"id":"nvidia/nemotron-cascade-2-30b-a3b","name":"NVIDIA Nemotron Cascade 2","lab":"nvidia","kind":"text","status":"ga","openWeights":true,"context":262144,"contextRange":null,"outputLimit":131072,"capabilities":{"reasoning":true,"toolCall":true,"structured":null,"attachment":false},"inputModalities":["text"],"reference":{"provider":"vultr","input":0.15,"output":0.6,"cacheRead":null,"official":false},"cheapest":{"provider":"vultr","input":0.15,"output":0.6,"cacheRead":null},"blendedRef":0.2625,"blendedMin":0.2625,"blendedTrusted":0.2625,"spread":null,"hostCount":1,"pricedHostCount":1,"aa":{"idx":17.8,"coding":25.3,"agentic":null,"speed":null,"ttft":null,"taskCost":null},"usage":null,"releaseDate":"2025-12-01","lastUpdated":"2025-12-01","url":"https://llmpricing.dev/m/nvidia/nemotron-cascade-2-30b-a3b/"}]}