Azure AI Foundry models & pricing
Azure AI Foundry hosts 157 models (145 with public pricing) covering 7 modalities. Azure marketplace catalog for Mistral, Cohere, Meta, Phi, and other partner models. Cheapest input starts at $0.0400/M tokens; the most premium goes up to $30.00/M. Use Future AGI's Agent Command Center to route any Azure AI Foundry model with cost-optimized fallback and unified observability.
157
chat 123
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Ministral 3B Deprecates in 35d | $0.0400/M | $0.0400/M | $0.0400/M | 128,000 | tools |
| Fw Nemotron Lightning 3.5 30B A3B | $0.0600/M | $0.220/M | $0.100/M | 262,144 | tools · reasoning · cache |
| Phi 4 mini Instruct | $0.0750/M | $0.300/M | $0.131/M | 131,072 | tools |
| Phi 4 mini Reasoning | $0.0750/M | $0.300/M | $0.131/M | 131,072 | tools |
| Phi 4 Multimodal Instruct | $0.0800/M | $0.320/M | $0.140/M | 131,072 | tools · vision · audio |
| Claude Haiku 5.5 | $0.1000/M | $0.500/M | $0.200/M | 1,000,000 | tools · vision · reasoning · cache |
| GPT-6 Luna | $0.1000/M | $0.500/M | $0.200/M | 922,000 | tools · vision · reasoning · cache |
| Mistral Small 2503 Deprecates in 35d | $0.1000/M | $0.300/M | $0.150/M | 128,000 | tools · vision |
| Phi 4 | $0.125/M | $0.500/M | $0.219/M | 16,384 | tools |
| Phi 4 Reasoning | $0.125/M | $0.500/M | $0.219/M | 32,768 | tools · reasoning |
| Phi 3.5 mini Instruct Deprecated | $0.130/M | $0.520/M | $0.228/M | 128,000 | |
| Phi 3.5 Vision Instruct Deprecated | $0.130/M | $0.520/M | $0.228/M | 128,000 | vision |
| Phi 3 mini 128K Instruct Deprecated | $0.130/M | $0.520/M | $0.228/M | 128,000 | |
| Phi 3 mini 4K Instruct Deprecated | $0.130/M | $0.520/M | $0.228/M | 4,096 | |
| Model Router | $0.140/M | — | — | 200,000 | |
| Fw DeepSeek V4 Flash | $0.150/M | $0.310/M | $0.190/M | 1,000,000 | tools · reasoning · cache |
| gpt-oss 120B | $0.150/M | $0.600/M | $0.262/M | 131,072 | tools |
| Mistral Nemo Deprecated | $0.150/M | $0.150/M | $0.150/M | 131,072 | tools |
| Phi 3 Small 128K Instruct Deprecated | $0.150/M | $0.600/M | $0.262/M | 128,000 | |
| Phi 3 Small 8K Instruct Deprecated | $0.150/M | $0.600/M | $0.262/M | 8,192 | |
| Phi 3.5 MOE Instruct Deprecated | $0.160/M | $0.640/M | $0.280/M | 128,000 | |
| Fw gpt-oss 120B | $0.165/M | $0.660/M | $0.289/M | 131,072 | tools · reasoning · cache |
| Phi 3 Medium 128K Instruct Deprecated | $0.170/M | $0.680/M | $0.298/M | 128,000 | |
| Phi 3 Medium 4K Instruct Deprecated | $0.170/M | $0.680/M | $0.298/M | 4,096 | |
| Fw GLM 5.3 Flash | $0.188/M | $0.625/M | $0.297/M | 1,048,576 | tools · reasoning · cache |
| DeepSeek V4 Flash | $0.190/M | $0.510/M | $0.270/M | 1,000,000 | tools · reasoning · cache |
| GPT-5.4 nano | $0.200/M | $1.25/M | $0.463/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5.4 nano (2026-03-17) | $0.200/M | $1.25/M | $0.463/M | 272,000 | tools · vision · reasoning · cache |
| Grok 4.1 Fast Non Reasoning | $0.200/M | $0.500/M | $0.275/M | 128,000 | tools |
| Grok 4.1 Fast Reasoning | $0.200/M | $0.500/M | $0.275/M | 128,000 | tools · reasoning |
| Grok 4 Fast Non Reasoning Deprecated | $0.200/M | $0.500/M | $0.275/M | — | |
| Grok 4 Fast Reasoning Deprecated | $0.200/M | $0.500/M | $0.275/M | — | |
| Grok Code Fast 1 | $0.200/M | $1.50/M | $0.525/M | 256,000 | tools |
| Llama 4 Scout 17B 16e Instruct | $0.200/M | $0.780/M | $0.345/M | 10,000,000 | tools · vision |
| MAI Code 1.1 Flash Deprecates in 35d | $0.200/M | $1.20/M | $0.450/M | 256,000 | tools · vision · reasoning · cache |
| Grok 3 mini (Global) | $0.250/M | $1.27/M | $0.505/M | 131,072 | tools · reasoning |
| Grok 3 mini Deprecated | $0.250/M | $1.27/M | $0.505/M | — | |
| Llama 4 Maverick 17B 128e Instruct FP8 | $0.250/M | $1.00/M | $0.438/M | 1,000,000 | tools · vision |
| Codestral 2501 | $0.300/M | $0.900/M | $0.450/M | 256,000 | |
| DeepSeek V4.1 Flash Deprecates in 41d | $0.300/M | $1.20/M | $0.525/M | 1,000,000 | tools · reasoning · cache |
| Llama 3.1 8B Instruct | $0.300/M | $0.610/M | $0.377/M | 128,000 | |
| Fw MiniMax M2.5 | $0.330/M | $1.32/M | $0.578/M | 1,000,000 | tools · reasoning · cache |
| Fw MiniMax M3 | $0.330/M | $1.32/M | $0.578/M | 512,000 | tools · vision · reasoning · cache |
| Llama 3.2 11B Vision Instruct | $0.370/M | $0.370/M | $0.370/M | 128,000 | tools · vision |
| Fw DeepSeek V4.1 Flash | $0.375/M | $1.50/M | $0.656/M | 1,000,000 | tools · reasoning · cache |
| Mistral Medium 2505 Deprecates in 35d | $0.400/M | $2.00/M | $0.800/M | 131,072 | tools |
| DeepSeek V4 Flash 0731 Deprecates in 29d | $0.440/M | $1.32/M | $0.660/M | 1,000,000 | tools · reasoning · cache |
| Jamba Instruct Deprecated | $0.500/M | $0.700/M | $0.550/M | 70,000 | |
| Mistral Large 3 | $0.500/M | $1.50/M | $0.750/M | 256,000 | tools · vision |
| DeepSeek v3.2 | $0.580/M | $1.68/M | $0.855/M | 128,000 | tools · reasoning · cache |
| DeepSeek V3.2 Speciale | $0.580/M | $1.68/M | $0.855/M | 128,000 | tools · reasoning · cache |
| Kimi K2.5 Deprecates in 83d | $0.600/M | $3.00/M | $1.20/M | 262,144 | tools · vision · cache |
| Kimi K2 Thinking Deprecated | $0.600/M | $2.50/M | $1.08/M | 262,144 | tools · reasoning |
| MAI Cyber 1 Flash | $0.600/M | $3.50/M | $1.33/M | 256,000 | tools · reasoning · cache |
| Fw DeepSeek v3.2 | $0.620/M | $1.85/M | $0.928/M | 163,840 | tools · reasoning · cache |
| Fw Kimi K2.5 | $0.660/M | $3.30/M | $1.32/M | 262,144 | tools · vision · reasoning · cache |
| Fw Nemotron 3 Ultra Nvfp4 | $0.660/M | $2.64/M | $1.16/M | 262,144 | tools · reasoning · cache |
| Llama 3.3 70B Instruct | $0.710/M | $0.710/M | $0.710/M | 128,000 | tools |
| GPT-5.4 mini | $0.750/M | $4.50/M | $1.69/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5.4 mini (2026-03-17) | $0.750/M | $4.50/M | $1.69/M | 272,000 | tools · vision · reasoning · cache |
| Command A Plus 05 2026 Deprecated | $0.800/M | $3.20/M | $1.40/M | 128,000 | tools · reasoning |
| Kimi K2.6 Deprecates in 163d | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning · cache |
| Kimi K2.7 Code Deprecates in 163d | $0.950/M | $4.00/M | $1.71/M | 262,144 | tools · vision · reasoning · cache |
| Claude Haiku 4.5 Deprecates in 11d | $1.00/M | $5.00/M | $2.00/M | 200,000 | tools · vision · reasoning · cache |
| Mistral Small Deprecated | $1.00/M | $3.00/M | $1.50/M | 32,000 | tools |
| Fw Kimi K2.6 | $1.05/M | $4.40/M | $1.88/M | 262,144 | tools · vision · reasoning · cache |
| Fw Kimi K2.7 Code | $1.05/M | $4.40/M | $1.89/M | 262,144 | tools · vision · reasoning · cache |
| Fw GLM 5 | $1.10/M | $3.52/M | $1.71/M | 200,000 | tools · reasoning · cache |
| Fw Inkling | $1.10/M | $4.46/M | $1.94/M | 1,048,576 | tools · reasoning · cache |
| Llama 3 70B Instruct Deprecated | $1.10/M | $0.370/M | $0.918/M | 8,192 | |
| DeepSeek V3 Deprecated | $1.14/M | $4.56/M | $2.00/M | 128,000 | |
| DeepSeek v3.0324 Deprecated | $1.14/M | $4.56/M | $2.00/M | — | |
| DeepSeek v3.1 Deprecated | $1.23/M | $4.94/M | $2.16/M | — | |
| Grok 4.20 Non Reasoning Deprecates in 153d | $1.25/M | $2.50/M | $1.56/M | 262,000 | tools · vision · cache |
| Grok 4.20 Reasoning Deprecates in 153d | $1.25/M | $2.50/M | $1.56/M | 262,000 | tools · vision · reasoning · cache |
| Grok 4.3 | $1.25/M | $2.50/M | $1.56/M | 200,000 | tools · vision · reasoning · cache |
| DeepSeek R1 Deprecated | $1.35/M | $5.40/M | $2.36/M | — | |
| MAI Ds R1 Deprecated | $1.35/M | $5.40/M | $2.36/M | 128,000 | reasoning |
| Mistral Medium 3.5 | $1.50/M | $7.50/M | $3.00/M | 128,000 | vision |
| Fw GLM 5.1 | $1.54/M | $4.84/M | $2.37/M | 202,800 | tools · reasoning · cache |
| Fw GLM 5.2 | $1.54/M | $4.84/M | $2.37/M | 1,048,576 | tools · reasoning · cache |
| DeepSeek V4 Pro | $1.74/M | $3.48/M | $2.18/M | 1,000,000 | tools · reasoning · cache |
| Fw GLM 5.3 | $1.75/M | $5.50/M | $2.69/M | 1,048,576 | tools · reasoning · cache |
| Fw DeepSeek V4 Pro | $1.93/M | $3.83/M | $2.40/M | 1,000,000 | tools · reasoning · cache |
| Claude Sonnet 5 | $2.00/M | $10.00/M | $4.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Sonnet 5.5 | $2.00/M | $10.00/M | $4.00/M | 1,000,000 | tools · vision · reasoning · cache |
| GPT-6.1 Sol | $2.00/M | $10.00/M | $4.00/M | 922,000 | tools · vision · reasoning · cache |
| GPT-6 Sol | $2.00/M | $10.00/M | $4.00/M | 922,000 | tools · vision · reasoning · cache |
| Grok 4.6 | $2.00/M | $6.00/M | $3.00/M | 200,000 | tools · vision · reasoning · cache |
| Grok 4.7 | $2.00/M | $6.00/M | $3.00/M | 500,000 | tools · vision · reasoning · cache |
| MAI Thinking 1 | $2.00/M | $8.00/M | $3.50/M | 256,000 | tools · reasoning · cache |
| Mistral Large 2407 Deprecated | $2.00/M | $6.00/M | $3.00/M | 128,000 | tools |
| Mistral Large latest | $2.00/M | $6.00/M | $3.00/M | 128,000 | tools |
| Llama 3.2 90B Vision Instruct | $2.04/M | $2.04/M | $2.04/M | 128,000 | tools · vision |
| Fw GLM 5.2 Fast | $2.31/M | $7.26/M | $3.55/M | 1,048,576 | tools · reasoning · cache |
| Command A | $2.50/M | $10.00/M | $4.38/M | 131,072 | tools |
| GPT-5.4 | $2.50/M | $15.00/M | $5.63/M | 922,000 | tools · vision · reasoning · cache |
| GPT-5.4 (2026-03-05) | $2.50/M | $15.00/M | $5.63/M | 922,000 | tools · vision · reasoning · cache |
| Llama 3.1 70B Instruct Deprecated | $2.68/M | $3.54/M | $2.90/M | 128,000 | |
| Claude Sonnet 4.5 Deprecates in 26d | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · vision · reasoning · cache |
| Claude Sonnet 4.6 Deprecates in 98d | $3.00/M | $15.00/M | $6.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Fw Kimi K3 | $3.00/M | $15.00/M | $6.00/M | 1,048,576 | tools · vision · reasoning · cache |
| Grok 3 (Global) | $3.00/M | $15.00/M | $6.00/M | 131,072 | tools |
| Grok 3 Deprecated | $3.00/M | $15.00/M | $6.00/M | — | |
| Grok 4 | $3.00/M | $15.00/M | $6.00/M | 262,000 | tools |
| Claude Opus 5.5 | $4.00/M | $20.00/M | $8.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Mistral Large Deprecated | $4.00/M | $12.00/M | $6.00/M | 32,000 | tools |
| Claude Opus 4.5 Deprecates in 20d | $5.00/M | $25.00/M | $10.00/M | 200,000 | tools · vision · reasoning · cache |
| Claude Opus 4.6 Deprecates in 90d | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 4.7 Deprecates in 153d | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 4.8 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 5 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| GPT-5.5 | $5.00/M | $30.00/M | $11.25/M | 922,000 | tools · vision · reasoning · cache |
| GPT-5.5 (2026-04-23) | $5.00/M | $30.00/M | $11.25/M | 922,000 | tools · vision · reasoning · cache |
| GPT-5.5 (2026-04-24) | $5.00/M | $30.00/M | $11.25/M | 922,000 | tools · vision · reasoning · cache |
| GPT (chat latest) | $5.00/M | $30.00/M | $11.25/M | 272,000 | tools · vision · reasoning · cache |
| Llama 3.1 405B Instruct | $5.33/M | $16.00/M | $8.00/M | 128,000 | |
| Claude Opus 5.5 Fast | $8.00/M | $40.00/M | $16.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Fable 5 | $10.00/M | $50.00/M | $20.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Fable 5.1 | $10.00/M | $50.00/M | $20.00/M | 1,000,000 | tools · vision · reasoning · cache |
| GPT-6 Astra | $10.00/M | $50.00/M | $20.00/M | 922,000 | tools · vision · reasoning · cache |
| Claude Opus 4.1 | $15.00/M | $75.00/M | $30.00/M | 200,000 | tools · vision · reasoning · cache |
| Jais 30B Chat Deprecated | — | — | — | 8,192 |
image generation 11
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| MAI Image 2.5 Flash Deprecated | $1.75/M | $19.50/M | $6.19/M | 32,000 | |
| MAI Image 2.6 Flash | $1.75/M | $19.00/M | $6.06/M | 32,000 | |
| GPT Image 2 | $5.00/M | $30.00/M | $11.25/M | — | vision |
| MAI Image 2.5 Deprecated | $5.00/M | $47.00/M | $15.50/M | 32,000 | |
| MAI Image 2.5 Pro Deprecated | $5.00/M | $106/M | $30.25/M | 32,000 | |
| MAI Image 2.6 | $5.00/M | $38.00/M | $13.25/M | 32,000 | |
| MAI Image 2e | $5.00/M | — | — | — | |
| Flux 1 Kontext Pro | — | — | — | 5,000 | |
| Flux 1.1 Pro | — | — | — | 5,000 | |
| Flux 2 Flex | — | — | — | 32,000 | |
| Flux 2 Pro | — | — | — | 32,000 |
ocr 9
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Cohere Parse v5 Deprecates in 41d | — | — | — | — | |
| Doc Intelligence Prebuilt Document | — | — | — | — | |
| Doc Intelligence Prebuilt Layout | — | — | — | — | |
| Doc Intelligence Prebuilt Read | — | — | — | — | |
| Mistral Document AI 2505 | — | — | — | — | |
| Mistral Document AI 2512 | — | — | — | — | |
| Mistral OCR 2505 | — | — | — | — | |
| Mistral OCR 2512 | — | — | — | — | |
| Mistral OCR 4.0 | — | — | — | — |
embedding 5
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Cohere Embed V5 Fast Deprecates in 80d | $0.0800/M | — | — | 128,000 | |
| Cohere Embed V3 English | $0.1000/M | — | — | 512 | |
| Cohere Embed V3 Multilingual | $0.1000/M | — | — | 512 | |
| Cohere Embed V5 Pro Deprecates in 80d | $0.120/M | — | — | 128,000 | |
| Embed V 4.0 | $0.120/M | — | — | 128,000 |
rerank 5
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Cohere Rerank V3 English Deprecated | — | — | — | 4,096 | |
| Cohere Rerank V3 Multilingual Deprecated | — | — | — | 4,096 | |
| Cohere Rerank v3.5 | — | — | — | 4,096 | |
| Cohere Rerank V4.0 Fast | — | — | — | 32,768 | |
| Cohere Rerank V4.0 Pro | — | — | — | 32,768 |
responses 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Codex mini Deprecates in 11d | $1.50/M | $6.00/M | $2.63/M | 200,000 | tools · vision · reasoning · cache |
| GPT-5.4 Pro | $30.00/M | $180/M | $67.50/M | 922,000 | tools · vision · reasoning · cache |
| GPT-5.4 Pro (2026-03-05) | $30.00/M | $180/M | $67.50/M | 922,000 | tools · vision · reasoning · cache |
audio transcription 1
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Whisper Deprecates in 41d | — | — | — | — |
FAQ
How many Azure AI Foundry models are there?
157 Azure AI Foundry models are listed across 7 modalities on this page. 145 have public per-token pricing.
How is Azure AI Foundry pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Azure AI Foundry model is cheapest?
Input pricing on Azure AI Foundry starts at $0.0400 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Azure AI Foundry via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Azure AI Foundry target, and call Azure AI Foundry models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.
Route any Azure AI Foundry model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.