← Providers
LLM Gateway
At a glance
Models hosted367With public price 367
Cheapest anywhere2
Model typesText / Chat 365Speech / Audio 2
Cheapest model hereLlama 3.2 3B Instruct (NovitaAI)
SDK package@ai-sdk/openai-compatible
APIhttps://api.llmgateway.io/v1
Hosted models by blended price asc
367 of 367
| Cheapest here? | |||||
|---|---|---|---|---|---|
| Llama 3.2 3B Instruct (NovitaAI)novita/llama-3.2-3b-instruct | $0.03 | $0.05 | — | 32,768 | Only channel |
| Qwen3.7 Flash (Alibaba Cloud)alibaba/qwen3.7-flash | $0.03 | $0.13 | $0.006 | 1,000,000 | Only channel |
| GPT OSS 120B (Runware)runware/gpt-oss-120b | $0.032 | $0.14 | $0.032 | 131,072 | Only channel |
| GPT OSS 20B (Together AI)together-ai/gpt-oss-20b | $0.05 | $0.20 | — | 131,072 | Only channel |
| InclusionAI Ling 3.0 Flash (DeepInfra)deepinfra/ling-3.0-flash | $0.06 | $0.18 | $0.012 | 262,144 | Only channel |
| InclusionAI Ling 3.0 Flash (NovitaAI)novita/ling-3.0-flash | $0.06 | $0.18 | $0.012 | 262,144 | Only channel |
| DeepSeek V4 Flash (Runware)runware/deepseek-v4-flash | $0.076 | $0.153 | $0.014 | 1,048,576 | Only channel |
| DeepSeek V4 Flash (Gonka24)gonka24/deepseek-v4-flash | $0.075 | $0.175 | $0.015 | 390,000 | Only channel |
| GLM-4 32B (0414-128k) (Z AI)zai/glm-4-32b-0414-128k | $0.10 | $0.10 | — | 128,000 | Only channel |
| Ministral 3B (Mistral AI)mistral/ministral-3b-2512 | $0.10 | $0.10 | — | 131,072 | Only channel |
| DeepSeek V4 Flash (DeepInfra)deepinfra/deepseek-v4-flash | $0.08 | $0.18 | $0.016 | 1,000,000 | Only channel |
| Nemotron 3 Nano 30B (Nebius AI)nebius/nemotron-3-nano-30b | $0.06 | $0.24 | — | 262,144 | Only channel |
| Nemotron 3 Nano Omni (Nebius AI)nebius/nemotron-3-nano-omni | $0.06 | $0.24 | — | 262,144 | Only channel |
| Qwen3.5 9B (DeepInfra)deepinfra/qwen3.5-9b | $0.10 | $0.15 | — | 262,144 | Only channel |
| Qwen3 Coder 30B A3B Instruct (NovitaAI)novita/qwen3-coder-30b-a3b-instruct | $0.07 | $0.27 | — | 160,000 | Only channel |
| Seed 1.6 Flash (250715) (ByteDance)bytedance/seed-1-6-flash-250715 | $0.07 | $0.30 | $0.015 | 256,000 | Only channel |
| GLM-4.6V FlashX (Z AI)zai/glm-4.6v-flashx | $0.04 | $0.40 | $0.004 | 128,000 | Only channel |
| Llama 3.2 11B Instruct (Inference.net)inference.net/llama-3.2-11b-instruct | $0.07 | $0.33 | — | 128,000 | Only channel |
| Gemma 4 26B A4B IT (DeepInfra)deepinfra/gemma-4-26b-a4b-it | $0.07 | $0.34 | — | 262,144 | Only channel |
| GPT-5 Nano (OpenAI)openai/gpt-5-nano | $0.05 | $0.40 | $0.005 | 400,000 | Only channel |
| Qwen Flash (Alibaba Cloud)alibaba/qwen-flash | $0.05 | $0.40 | $0.01 | 1,000,000 | Only channel |
| Qwen3 VL Flash (Alibaba Cloud)alibaba/qwen3-vl-flash | $0.05 | $0.40 | $0.01 | 262,144 | Only channel |
| GPT-5 Nano (Azure)azure/gpt-5-nano | $0.05 | $0.40 | $0.005 | 400,000 | Only channel |
| MiniMax M2.7 (Gonka24)gonka24/minimax-m2.7 | $0.08 | $0.32 | $0.017 | 204,800 | Only channel |
| GLM-4.7 Flash (EmberCloud)embercloud/glm-4.7-flash | $0.06 | $0.40 | $0.01 | 200,000 | Only channel |
| Ministral 8B (Mistral AI)mistral/ministral-8b-2512 | $0.15 | $0.15 | — | 262,144 | Only channel |
| Qwen3 32B (Nebius AI)nebius/qwen3-32b | $0.10 | $0.30 | — | 40,960 | Only channel |
| Cosmos 3 Super Reasoner (Nebius AI)nebius/cosmos3-super-reasoner | $0.10 | $0.30 | — | 262,144 | Only channel |
| Qwen3 30B A3B Instruct 2507 (Nebius AI)nebius/qwen3-30b-a3b-instruct-2507 | $0.10 | $0.30 | — | 262,000 | Only channel |
| Gemma 3 27B (Nebius AI)nebius/gemma-3-27b | $0.10 | $0.30 | — | 110,000 | Only channel |
| Mistral Small 3.2 (Mistral AI)mistral/mistral-small-2506 | $0.10 | $0.30 | — | 128,000 | Only channel |
| Gemma 4 31B IT (Runware)runware/gemma-4-31b-it | $0.102 | $0.297 | $0.012 | 262,144 | Only channel |
| GLM-4.7 FlashX (Z AI)zai/glm-4.7-flashx | $0.07 | $0.40 | $0.01 | 200,000 | Only channel |
| DeepSeek V4 Flash (Fireworks AI)fireworks/deepseek-v4-flash | $0.14 | $0.28 | $0.028 | 1,048,576 | Only channel |
| DeepSeek V4 Flash (DeepSeek)deepseek/deepseek-v4-flash | $0.14 | $0.28 | $0.0028 | 1,050,000 | Lowest anywhere |
| Gemini 2.5 Flash Lite (Google Vertex AI)google-vertex/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.01 | 1,048,576 | Only channel |
| DeepSeek V4 Flash (NovitaAI)novita/deepseek-v4-flash | $0.14 | $0.28 | $0.028 | 1,050,000 | Only channel |
| GPT-4.1 Nano (OpenAI)openai/gpt-4.1-nano | $0.10 | $0.40 | $0.025 | 1,000,000 | Only channel |
| DeepSeek V4 Flash (Together AI)together-ai/deepseek-v4-flash | $0.14 | $0.28 | $0.03 | 163,840 | Only channel |
| Gemini 2.5 Flash Lite (Google AI Studio)google-ai-studio/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.01 | 1,048,576 | Only channel |
| DeepSeek V4 Flash (CanopyWave)canopywave/deepseek-v4-flash | $0.14 | $0.28 | $0.03 | 1,000,000 | Only channel |
| MiMo V2.5 (Xiaomi)xiaomi/mimo-v2.5 | $0.14 | $0.28 | $0.0028 | 1,000,000 | Only channel |
| GPT-4.1 Nano (Azure)azure/gpt-4.1-nano | $0.10 | $0.40 | $0.025 | 1,000,000 | Only channel |
| DeepSeek V4 Flash (Baidu)baidu/deepseek-v4-flash | $0.14 | $0.28 | $0.028 | 1,048,576 | Only channel |
| Gemma 4 31B IT (DeepInfra)deepinfra/gemma-4-31b-it | $0.13 | $0.38 | — | 262,144 | Only channel |
| Gemma 4 26B A4B IT (NovitaAI)novita/gemma-4-26b-a4b-it | $0.13 | $0.40 | — | 262,144 | Only channel |
| Llama 3.3 70B Instruct (Nebius AI)nebius/llama-3.3-70b-instruct | $0.13 | $0.40 | — | 128,000 | Only channel |
| Hermes 4 70B (Nebius AI)nebius/hermes-4-70b | $0.13 | $0.40 | — | 131,072 | Only channel |
| GPT OSS 120B (ByteDance)bytedance/gpt-oss-120b | $0.10 | $0.50 | $0.02 | 128,000 | Only channel |
| Ministral 14B (Mistral AI)mistral/ministral-14b-2512 | $0.20 | $0.20 | — | 262,144 | Only channel |
| GPT OSS 20B (Groq)groq/gpt-oss-20b | $0.10 | $0.50 | — | 131,072 | Only channel |
| Llama 3.3 70B Instruct (NovitaAI)novita/llama-3.3-70b-instruct | $0.135 | $0.40 | — | 131,072 | Only channel |
| Gemma 4 31B IT (NovitaAI)novita/gemma-4-31b-it | $0.14 | $0.40 | — | 262,144 | Only channel |
| MiniMax M2.1 Lightning (MiniMax)minimax/minimax-m2.1-lightning | $0.12 | $0.48 | — | 196,608 | Only channel |
| Qwen3 235B A22B Instruct 2507 (NovitaAI)novita/qwen3-235b-a22b-instruct-2507 | $0.09 | $0.58 | — | 131,072 | Only channel |
| Qwen3 Coder Next (EmberCloud)embercloud/qwen3-coder-next | $0.108 | $0.675 | $0.06 | 262,144 | Only channel |
| Hy3 (DeepInfra)deepinfra/hy3 | $0.14 | $0.58 | $0.035 | 262,144 | Only channel |
| Hy3 (NovitaAI)novita/hy3 | $0.14 | $0.58 | $0.035 | 262,144 | Only channel |
| DeepSeek V4 Flash (Alibaba Cloud)alibaba/deepseek-v4-flash | $0.20 | $0.40 | $0.04 | 1,000,000 | 1.4× pricier |
| Qwen3 VL 30B A3B Instruct (DeepInfra)deepinfra/qwen3-vl-30b-a3b-instruct | $0.15 | $0.60 | — | 262,144 | Only channel |
| GPT-4o Mini (OpenAI)openai/gpt-4o-mini | $0.15 | $0.60 | $0.075 | 128,000 | Only channel |
| GPT-4o Mini Search Preview (OpenAI)openai/gpt-4o-mini-search-preview | $0.15 | $0.60 | — | 128,000 | Only channel |
| GPT OSS 120B (Together AI)together-ai/gpt-oss-120b | $0.15 | $0.60 | — | 131,072 | Only channel |
| GPT OSS 120B (Nebius AI)nebius/gpt-oss-120b | $0.15 | $0.60 | — | 131,072 | Only channel |
| GPT OSS 120B (Azure)azure/gpt-oss-120b | $0.15 | $0.60 | — | 131,072 | Only channel |
| GPT OSS 120B (SCX.ai (Turbo))scx-ai/gpt-oss-120b | $0.17 | $0.55 | — | 131,072 | Only channel |
| Grok 4.1 Fast Reasoning (Azure AI Foundry)azure-ai-foundry/grok-4-1-fast-reasoning | $0.20 | $0.50 | — | 2,000,000 | Only channel |
| Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)azure-ai-foundry/grok-4-1-fast-non-reasoning | $0.20 | $0.50 | — | 2,000,000 | Only channel |
| Llama 4 Scout 17B Instruct (NovitaAI)novita/llama-4-scout-17b-instruct | $0.18 | $0.59 | — | 131,072 | Only channel |
| DeepSeek V3.2 (DeepInfra)deepinfra/deepseek-v3.2 | $0.26 | $0.38 | $0.13 | 160,000 | Only channel |
| Llama 4 Scout 17B Instruct (AWS Bedrock)aws-bedrock/llama-4-scout-17b-instruct | $0.17 | $0.66 | — | 8,192 | Only channel |
| GPT OSS 120B (Groq)groq/gpt-oss-120b | $0.15 | $0.75 | — | 131,072 | Only channel |
| Qwen3 235B A22B Instruct 2507 (Nebius AI)nebius/qwen3-235b-a22b-instruct-2507 | $0.20 | $0.60 | — | 262,000 | Only channel |
| DeepSeek V3.2 (NovitaAI)novita/deepseek-v3.2 | $0.269 | $0.40 | $0.135 | 163,840 | Only channel |
| GLM-4.5 Air (EmberCloud)embercloud/glm-4.5-air | $0.13 | $0.85 | $0.025 | 131,000 | Only channel |
| DeepSeek V3.2 (ByteDance)bytedance/deepseek-v3.2 | $0.28 | $0.42 | $0.056 | 131,072 | Only channel |
| Qwen3 VL 30B A3B Instruct (NovitaAI)novita/qwen3-vl-30b-a3b-instruct | $0.20 | $0.70 | — | 131,072 | Only channel |
| Qwen3 235B A22B FP8 (NovitaAI)novita/qwen3-235b-a22b-fp8 | $0.20 | $0.80 | — | 40,960 | Only channel |
| Qwen Omni Turbo (Alibaba Cloud)alibaba/qwen-omni-turbo | $0.20 | $0.80 | — | 32,768 | Only channel |
| Qwen3 VL 235B A22B Instruct (DeepInfra)deepinfra/qwen3-vl-235b-a22b-instruct | $0.20 | $0.88 | $0.11 | 262,144 | Only channel |
| Qwen2.5 VL 72B Instruct (Nebius AI)nebius/qwen2-5-vl-72b-instruct | $0.25 | $0.75 | — | 32,000 | Only channel |
| Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))vertex-openai/qwen3-235b-a22b-instruct-2507 | $0.22 | $0.88 | — | 262,144 | Only channel |
| MiniMax M2 (MiniMax)minimax/minimax-m2 | $0.20 | $1.00 | $0.03 | 196,608 | Only channel |
| Qwen3 Next 80B A3B Thinking (Nebius AI)nebius/qwen3-next-80b-a3b-thinking | $0.15 | $1.20 | — | 131,072 | Only channel |
| Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))vertex-openai/qwen3-next-80b-a3b-thinking | $0.15 | $1.20 | — | 131,072 | Only channel |
| Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))vertex-openai/qwen3-next-80b-a3b-instruct | $0.15 | $1.20 | — | 131,072 | Only channel |
| Llama 4 Maverick 17B Instruct (NovitaAI)novita/llama-4-maverick-17b-instruct | $0.27 | $0.85 | — | 1,048,576 | Only channel |
| Llama 4 Maverick 17B Instruct (AWS Bedrock)aws-bedrock/llama-4-maverick-17b-instruct | $0.24 | $0.97 | — | 8,192 | Only channel |
| GLM-4.5 Air (Z AI)zai/glm-4.5-air | $0.20 | $1.10 | $0.03 | 128,000 | Only channel |
| MiniMax Text 01 (MiniMax)minimax/minimax-text-01 | $0.20 | $1.10 | — | 1,000,000 | Only channel |
| Kimi K2.6 (Gonka24)gonka24/kimi-k2.6 | $0.22 | $1.14 | $0.048 | 262,144 | Only channel |
| GLM-4.6V (NovitaAI)novita/glm-4.6v | $0.30 | $0.90 | $0.055 | 131,072 | Only channel |
| GLM-4.6V (Z AI)zai/glm-4.6v | $0.30 | $0.90 | $0.05 | 128,000 | Only channel |
| Nemotron 3 Super 120B (Nebius AI)nebius/nemotron-3-super-120b | $0.30 | $0.90 | — | 262,144 | Only channel |
| Codestral (Mistral AI)mistral/codestral-2508 | $0.30 | $0.90 | — | 256,000 | Only channel |
| GPT OSS 120B (Cerebras)cerebras/gpt-oss-120b | $0.35 | $0.75 | — | 131,072 | Only channel |
| GPT-5.6 Luna (OpenAI)openai/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | 1,050,000 | Only channel |
| GPT-5.6 Luna (Azure)azure/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | 1,050,000 | Only channel |
| Gemma 4 31B IT (SCX.ai (Turbo))scx-ai/gemma-4-31b-it | $0.30 | $0.91 | — | 131,072 | Only channel |
| GPT-5.4 Nano (OpenAI)openai/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | 400,000 | Only channel |
| GPT-5.4 Nano (Azure)azure/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | 400,000 | Only channel |
| MiniMax M2.1 (MiniMax)minimax/minimax-m2.1 | $0.27 | $1.10 | — | 196,608 | Only channel |
| Qwen3 Next 80B A3B Instruct (NovitaAI)novita/qwen3-next-80b-a3b-instruct | $0.15 | $1.50 | — | 131,072 | Only channel |
| Qwen3 32B (SCX.ai (Turbo))scx-ai/qwen3-32b | $0.36 | $0.87 | — | 32,768 | Only channel |
| GPT-5.6 Luna (AWS Mantle)aws-mantle/gpt-5.6-luna | $0.22 | $1.32 | $0.022 | 278,528 | Only channel |
| MiniMax M2.7 (NovitaAI)novita/minimax-m2.7 | $0.30 | $1.20 | $0.06 | 204,800 | Only channel |
| MiniMax M2.5 (NovitaAI)novita/minimax-m2.5 | $0.30 | $1.20 | $0.03 | 204,800 | Only channel |
| MiniMax M2.1 (NovitaAI)novita/minimax-m2.1 | $0.30 | $1.20 | $0.03 | 204,800 | Only channel |
| MiniMax M3 (Together AI)together-ai/minimax-m3 | $0.30 | $1.20 | $0.06 | 524,288 | Only channel |
| MiniMax M3 (Nebius AI)nebius/minimax-m3 | $0.30 | $1.20 | — | 1,048,576 | Only channel |
| MiniMax M2.5 (Nebius AI)nebius/minimax-m2.5 | $0.30 | $1.20 | — | 196,608 | Only channel |
| MiniMax M2.7 (MiniMax)minimax/minimax-m2.7 | $0.30 | $1.20 | $0.06 | 204,800 | Only channel |
| MiniMax M2.5 (MiniMax)minimax/minimax-m2.5 | $0.30 | $1.20 | $0.03 | 204,800 | Only channel |
| Gemma 4 31B IT (Together AI)together-ai/gemma-4-31b-it | $0.39 | $0.97 | — | 262,144 | Only channel |
| DeepSeek V4 Pro (DeepSeek)deepseek/deepseek-v4-pro | $0.435 | $0.87 | $0.0036 | 1,050,000 | Lowest anywhere |
| MiMo V2.5 Pro (Xiaomi)xiaomi/mimo-v2.5-pro | $0.435 | $0.87 | $0.0036 | 1,000,000 | Only channel |
| Qwen3 VL Plus (Alibaba Cloud)alibaba/qwen3-vl-plus | $0.20 | $1.60 | $0.04 | 262,144 | Only channel |
| Qwen3.6 35B A3B (NovitaAI)novita/qwen3.6-35b-a3b | $0.248 | $1.49 | — | 262,144 | Only channel |
| Qwen3.6 35B A3B (Alibaba Cloud)alibaba/qwen3.6-35b-a3b | $0.248 | $1.49 | — | 262,144 | Only channel |
| Gemini 3.1 Flash Lite (Google Vertex AI)google-vertex/gemini-3.1-flash-lite | $0.25 | $1.50 | $0.025 | 1,048,576 | Only channel |