LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Providers
ai

AI/ML API

aimlapi·Gateway·181 models·Official docs ↗

AI/ML API is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.

It lists 181 models on this page. Coverage spans text and chat (178), classification and safety (1), speech and audio (1), and image generation (1). The lowest-priced model hosted here is Granite-4.0-H-Micro.

AI/ML API is the lowest paid channel for 1 model that has at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.

Coverage & pricing
Models hosted181With public price 181
Cheapest anywhere1
Model typesText / Chat 178Classify / Safety 1Speech / Audio 1Image gen 1
Cheapest model hereibGranite-4.0-H-Micro
SDK package@ai-sdk/openai-compatible
APIhttps://api.aimlapi.com/v1

Hosted models by blended price asc

⌕
181 of 181
Cheapest here?
ibGranite-4.0-H-Microibm-granite/granite-4.0-h-micro$0.023$0.15—131,0001.4× pricier
saLlama 3 8B Lunarissao10k/l3-lunaris-8b$0.069$0.069—8,1921.6× pricier
upSolar Pro 4upstage/solar-pro4$0.041$0.17$0.0083524,2881.4× pricier
Mistral Small 3mistralai/mistral-small-24b-instruct-2501$0.069$0.11—32,7681.4× pricier
inSchematron V2 Turboinference-net/schematron-v2-turbo$0.041$0.21—128,0001.4× pricier
Nova Micro 1.0amazon/nova-micro-v1$0.048$0.19—128,0001.4× pricier
Gemma 3 4B ITgoogle/gemma-3-4b-it$0.069$0.14$0.055131,0001.7× pricier
Command R7Bcohere/command-r7b-12-2024$0.052$0.21—128,0001.4× pricier
Gemma 3 12B ITgoogle/gemma-3-12b-it$0.069$0.21$0.055131,0001.7× pricier
Hy-MT2-1.8Btencent/hy-mt2-1.8b$0.061$0.24—8,1921.4× pricier
inSchematron V2 Smallinference-net/schematron-v2-small$0.069$0.32—128,0001.4× pricier
reReka Edgerekaai/reka-edge$0.14$0.14—16,3841.4× pricier
Nova Lite 1.0amazon/nova-lite-v1$0.083$0.33—300,0001.4× pricier
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct$0.10$0.28—128,0001.1× pricier
Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b$0.10$0.41—8,1921.4× pricier
Hy-MT2-7Btencent/hy-mt2-7b$0.10$0.41—8,1921.4× pricier
Qwen3 VL Flash (Alibaba Cloud)alibaba/qwen3-vl-flash$0.065$0.52$0.065262,1442.5× pricier
GPT OSS 20Bopenai/gpt-oss-20b$0.10$0.41$0.052131,00010.0× pricier
GPT OSS Safeguard 20BClassify / Safetyopenai/gpt-oss-safeguard-20b$0.10$0.41$0.052131,0721.8× pricier
bySeed 1.6 Flashbytedance-seed/seed-1.6-flash$0.10$0.41—262,1442.5× pricier
Voxtral Small 24B 2507Speech / Audiomistralai/voxtral-small-24b-2507$0.14$0.41$0.01432,0001.4× pricier
Ministral 3 3B 2512mistralai/ministral-3b-2512$0.21$0.21$0.014131,0722.1× pricier
GPT-5 Nanoopenai/gpt-5-nano$0.076$0.61$0.069400,0001.9× pricier
Mistral Nemomistralai/mistral-nemo$0.21$0.23$0.21128,0009.5× pricier
GPT-4.1 nanoopenai/gpt-4.1-nano$0.13$0.52$0.0331,000,0001.8× pricier
bySeed 2.0 Minibytedance-seed/seed-2.0-mini$0.14$0.55—262,1442.5× pricier
MiMo-V2.5xiaomi/mimo-v2.5$0.19$0.39$0.00391,000,0001.5× pricier
Claude Haiku 5.5anthropic/claude-haiku-5.5$0.13$0.65$0.0131,000,0001.3× pricier
GPT-6 Lunaopenai/gpt-6-luna$0.13$0.65$0.0131,050,0001.6× pricier
GLM-4.7-Flashz-ai/glm-4.7-flash$0.17$0.69$0.014202,7522.1× pricier
GLM-5.3-Flashz-ai/glm-5.3-flash$0.20$0.65$0.0391,048,5766.5× pricier
Qwen3.8 Flashalibaba/qwen3.8-flash$0.21$0.61$0.0211,000,0001.7× pricier
Gemma 3 27B ITgoogle/gemma-3-27b-it$0.21$0.63$0.10128,0003.1× pricier
GPT-4o miniopenai/gpt-4o-mini$0.20$0.78$0.098128,0002.6× pricier
Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it$0.21$0.83$0.21262,1444.2× pricier
Command Rcohere/command-r-08-2024$0.21$0.83—128,0001.4× pricier
upSolar Pro 3upstage/solar-pro-3$0.21$0.83$0.021128,0001.4× pricier
Ministral 3 8B 2512mistralai/ministral-8b-2512$0.41$0.41$0.021262,1442.8× pricier
Sabamistralai/mistral-saba$0.28$0.83$0.02832,7681.4× pricier
Mistral Small 4mistralai/mistral-small-2603$0.26$1.03$0.021262,1443.7× pricier
Mercury 2.5inception/mercury-2.5$0.28$1.03$0.028260,0006.9× pricier
Hy3tencent/hy3$0.28$1.10$0.069262,1444.2× pricier
Ministral 3 14B 2512mistralai/ministral-14b-2512$0.48$0.48$0.028262,1442.4× pricier
thCydonia 24B V4.1thedrummer/cydonia-24b-v4.1$0.41$0.69$0.21131,0721.4× pricier
Mercury 2inception/mercury-2$0.34$1.03$0.034128,0001.4× pricier
coUncensoredcognitivecomputations/dolphin-mistral-24b-venice-edition$0.28$1.24—128,0001.4× pricier
Qwen3-Next 80B-A3B Instructalibaba/qwen3-next-80b-a3b-instruct$0.20$1.56—129,0242.1× pricier
thUnslopNemo 12Bthedrummer/unslopnemo-12b$0.55$0.55—32,7681.4× pricier
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct$0.48$0.76—128,0003.7× pricier
GPT-5.6 Lunaopenai/gpt-5.6-luna$0.26$1.56$0.0261,050,0004.3× pricier
GPT-5.6 Lunaopenai/gpt-5.6-luna-pro$0.28$1.65$0.0281,050,0004.5× pricier
GLM-4.6Vz-ai/glm-4.6v$0.41$1.24$0.076131,0723.0× pricier
Codestral 25.08mistralai/codestral-2508$0.41$1.24$0.041256,0001.4× pricier
GPT-5.4 nanoopenai/gpt-5.4-nano$0.28$1.72$0.028400,0001.7× pricier
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash$0.39$1.56$0.00781,048,57613.6× pricier
DeepSeek V4 Flashdeepseek/deepseek-chat$0.39$1.56$0.00781,000,00015.6× pricier
DeepSeek V4 Flashdeepseek/deepseek-v4-flash$0.39$1.56$0.00781,000,00015.6× pricier
GPT OSS 120Bopenai/gpt-oss-120b$0.48$1.31$0.48131,00011.7× pricier
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324$0.40$1.57$0.19128,0001.4× pricier
MiMo-V2.5-Proxiaomi/mimo-v2.5-pro$0.60$1.20$0.0051,000,0002.5× pricier
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview$0.34$2.06$0.0341,000,0002.8× pricier
unReMM SLERP 13Bundi95/remm-slerp-l2-13b$0.69$1.03—6,1441.8× pricier
Qwen Plusalibaba/qwen-plus$0.52$1.56$0.10131,0004.9× pricier
thSkyfall 36B V2thedrummer/skyfall-36b-v2$0.76$1.10$0.3432,7681.4× pricier
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp$0.57$1.72$0.0181,048,5767.8× pricier
Muse Glimmer 30Bmeta/muse-glimmer-30b$0.48$2.06$0.055131,0722.5× pricier
Gemma 2 27Bgoogle/gemma-2-27b-it$0.89$0.89—8,1921.4× pricier
GPT-4.1 miniopenai/gpt-4.1-mini$0.52$2.08$0.131,000,0001.6× pricier
saLlama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b$0.89$1.03—131,0721.9× pricier
bySeed 2.0 Litebytedance-seed/seed-2.0-lite$0.34$2.75—262,1444.7× pricier
noHermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b$0.96$0.96—131,0722.4× pricier
GPT-3.5-turboopenai/gpt-3.5-turbo$0.65$1.95—16,0001.4× pricier
GPT-5 Miniopenai/gpt-5-mini$0.38$3.03$0.34400,00010.1× pricier
Inkling Smallthinkingmachines/inkling-small$0.80$1.98$0.16524,2881.7× pricier
Mistral Medium 3mistralai/mistral-medium-3$0.55$2.75$0.055131,0721.4× pricier
Mistral Medium 3.1mistralai/mistral-medium-3.1$0.55$2.75$0.055131,0721.4× pricier
maWeaver (alpha)mancer/weaver$1.03$1.38—8,0002.3× pricier
Devstral 2mistralai/devstral-2512$0.61$3.03$0.061262,1441.5× pricier
GLM-4.5Vz-ai/glm-4.5v$0.83$2.48$0.1565,5362.9× pricier
moMorph V3 Fastmorph/morph-v3-fast$1.10$1.65—81,9201.4× pricier
Sonarperplexity/sonar$1.30$1.30—128,0001.6× pricier
reRelace Apply 3relace/relace-apply-3$1.17$1.72—256,0001.4× pricier
Llama-3.3-70B-Instructmeta-llama/Llama-3.3-70B-Instruct-Turbo$1.35$1.35—128,00014.2× pricier
noHermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b$1.38$1.38—131,0721.4× pricier
aiAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b$1.10$2.20—32,7681.4× pricier
Kimi K2 0711moonshotai/kimi-k2$0.78$3.16—131,0721.8× pricier
Qwen3.6 Max Previewalibaba/qwen3.6-max-preview$0.65$3.90—262,144Lowest anywhere
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking$0.83$3.44$0.21262,1441.7× pricier
Gemma 4 31B ITgoogle/gemma-4-31b-it$1.36$2.05$1.36256,00011.2× pricier
bySeed 2.0 Codebytedance-seed/seed-2.0-code$0.69$4.13—262,1441.7× pricier
Qwen3.8 27Balibaba/qwen3.8-27b$0.62$4.40—262,14413.8× pricier
moMorph V3 Largemorph/morph-v3-large$1.24$2.61—262,1441.4× pricier
Hy4 previewtencent/hy4-preview$1.15$3.44$0.0581,048,5761.7× pricier
DeepSeek V4 Prodeepseek/deepseek-v4-pro$1.17$3.51$0.0391,000,0004.0× pricier
Nova Pro 1.0amazon/nova-pro-v1$1.10$4.40—300,0001.4× pricier
Gemini 3.8 Flashgoogle/gemini-3-8-flash$0.98$4.88$0.0981,048,5761.3× pricier
Gemini 3.8 Flashgoogle/gemini-3.8-flash$0.98$4.88$0.0981,048,5761.3× pricier
Gemini 3.7 Flashgoogle/gemini-3.7-flash$0.98$4.88$0.0981,048,5761.3× pricier
Step 5 Previewstepfun/step-5-preview$1.38$3.71$0.0691,000,0001.4× pricier
saLlama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b$1.99$1.99—131,0722.3× pricier
Grok 4.20 (Non-Reasoning)x-ai/grok-4-20-0309-non-reasoning$1.63$3.25$0.262,000,0001.3× pricier
X-Ai/Grok-4-Fast-Non-Reasoningx-ai/grok-4-fast-non-reasoning$1.63$3.25$0.262,000,0008.2× pricier
Kimi K2 Instruct 0905moonshotai/kimi-k2-0905$1.38$4.13—262,1442.8× pricier
reRelace Searchrelace/relace-search$1.38$4.13—256,0001.4× pricier
Inklingthinkingmachines/inkling$1.38$5.57$0.231,048,5761.4× pricier
GLM-5-Turboz-ai/glm-5-turbo$1.56$5.20$0.31262,1441.8× pricier
GLM-5V-Turboz-ai/glm-5v-turbo$1.56$5.20$0.31202,7521.9× pricier
o3-miniopenai/o3-mini$1.43$5.72$0.72200,0001.4× pricier
grMythoMax L2 13Bgryphe/mythomax-l2-13b$2.58$2.58$2.584,09629.5× pricier
Claude Haiku 4.5 (latest)anthropic/claude-haiku-4.5$1.38$6.88$0.14200,0002.0× pricier
Muse Spark 1.2meta/muse-spark-1.2$1.72$5.85$0.211,048,57622.0× pricier
Muse Spark 1.3meta/muse-spark-1.3$1.72$5.85$0.211,048,57622.0× pricier
Muse Spark 1.1meta/muse-spark-1.1$1.72$5.85$0.211,048,5761.4× pricier
GLM-5.2zhipu/glm-5.2$1.82$5.72$0.341,000,0005.7× pricier
GLM-5.3zhipu/glm-5.3$1.82$5.72$0.341,024,0004.3× pricier
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813$2.39$4.79$0.201,048,5766.5× pricier
Qwen3 Maxalibaba/qwen3-max$1.56$7.80$0.31262,1445.0× pricier
Qwen3 Max Previewalibaba/qwen3-max-preview$1.56$7.80$0.31252,0001.6× pricier
Qwen Maxalibaba/qwen-max$2.08$8.32$0.4232,0006.0× pricier
Gemini 3.6 Flashgoogle/gemini-3.6-flash$1.95$9.75$0.201,048,5765.2× pricier