Azure AI Foundry model pricing
As of October 10, 2026, 133 Azure AI Foundry models are available through LiteLLM. The most recently added are Cohere Embed V5 Fast, Cohere Embed V5 Pro, GPT-6.1 Sol. Prices below are Azure AI Foundry's list prices.
Azure AI Foundry models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| Cohere Embed V5 Fast | – | $0.08 per 1M tokens | 128K | 1 | Oct 2026 |
| Cohere Embed V5 Pro | – | $0.12 per 1M tokens | 128K | 1 | Oct 2026 |
| GPT-6.1 Sol | OpenAI | $2 / $10 per 1M tokens | 922K | 8 | Sep 2026 |
| Claude Sonnet 5.5 | Anthropic | $2 / $10 per 1M tokens | 1M | 7 | Sep 2026 |
| Mai Cyber 1 Flash | – | $0.60 / $3.50 per 1M tokens | 256K | 1 | Sep 2026 |
| Cohere Command A Plus | – | $0.80 / $3.20 per 1M tokens | 128K | 1 | Sep 2026 |
| Fw DeepSeek V4 Flash | – | $0.15 / $0.31 per 1M tokens | 1M | 1 | Sep 2026 |
| Fw DeepSeek V4.1 Flash | – | $0.375 / $1.50 per 1M tokens | 1M | 1 | Sep 2026 |
| Fw GLM 5.3 | – | $1.75 / $5.50 per 1M tokens | 1M | 1 | Sep 2026 |
| Fw GLM 5.3 Flash | – | $0.188 / $0.625 per 1M tokens | 1M | 1 | Sep 2026 |
| Fw GPT OSS 120B | – | $0.165 / $0.66 per 1M tokens | 128K | 1 | Sep 2026 |
| Mai Image 2.6 | – | $5 per 1M input tokens | 32K | 1 | Sep 2026 |
| Mai Image 2.6 Flash | – | $1.75 per 1M input tokens | 32K | 1 | Sep 2026 |
| Claude Opus 5.5 | Anthropic | $4 / $20 per 1M tokens | 1M | 8 | Sep 2026 |
| GPT-6 Luna | OpenAI | $0.10 / $0.50 per 1M tokens | 922K | 8 | Sep 2026 |
| GPT-6 Sol | OpenAI | $2 / $10 per 1M tokens | 922K | 8 | Sep 2026 |
| Grok 4.7 | xAI | $2 / $6 per 1M tokens | 500K | 5 | Sep 2026 |
| Mai Image 2.5 Pro | – | $0.1085 per image | 32K | 1 | Sep 2026 |
| Flux.2 Flex | Black Forest Labs | – | 32K | 1 | Sep 2026 |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 / $1.20 per 1M tokens | 1M | 8 | Sep 2026 |
| Cohere Command A | – | $2.50 / $10 per 1M tokens | 128K | 1 | Sep 2026 |
| GPT Chat | OpenAI | $5 / $30 per 1M tokens | 272K | 3 | Sep 2026 |
| Cohere Parse V5 | – | – | – | 1 | Sep 2026 |
| Fw Nemotron Lightning 3.5 30B A3B | – | $0.06 / $0.22 per 1M tokens | 256K | 1 | Sep 2026 |
| GPT-6 Astra | OpenAI | $10 / $50 per 1M tokens | 922K | 8 | Sep 2026 |
| Mai Thinking 1 | – | $2 / $8 per 1M tokens | 256K | 2 | Sep 2026 |
| Claude Fable 5.1 | Anthropic | $10 / $50 per 1M tokens | 1M | 7 | Sep 2026 |
| Fw DeepSeek V3.2 | – | $0.62 / $1.85 per 1M tokens | 160K | 1 | Aug 2026 |
| Fw DeepSeek V4 Pro | – | $1.925 / $3.828 per 1M tokens | 1M | 1 | Aug 2026 |
| Fw GLM 5 | – | $1.10 / $3.52 per 1M tokens | 200K | 1 | Aug 2026 |
| Fw GLM 5.1 | – | $1.54 / $4.84 per 1M tokens | 203K | 1 | Aug 2026 |
| Fw GLM 5.2 | – | $1.54 / $4.84 per 1M tokens | 1M | 1 | Aug 2026 |
| Fw GLM 5.2 Fast | – | $2.31 / $7.26 per 1M tokens | 1M | 1 | Aug 2026 |
| Fw Inkling | – | $1.10 / $4.46 per 1M tokens | 1M | 1 | Aug 2026 |
| Fw Kimi K2.5 | – | $0.66 / $3.30 per 1M tokens | 256K | 1 | Aug 2026 |
| Fw Kimi K2.6 | – | $1.045 / $4.40 per 1M tokens | 256K | 1 | Aug 2026 |
| Fw Kimi K2.7 Code | – | $1.05 / $4.40 per 1M tokens | 256K | 1 | Aug 2026 |
| Fw Kimi K3 | – | $3 / $15 per 1M tokens | 1M | 1 | Aug 2026 |
| Fw MiniMax M2.5 | – | $0.33 / $1.32 per 1M tokens | 1M | 1 | Aug 2026 |
| Fw MiniMax M3 | – | $0.33 / $1.32 per 1M tokens | 512K | 1 | Aug 2026 |
| Fw Nemotron 3 Ultra | – | $0.66 / $2.64 per 1M tokens | 256K | 1 | Aug 2026 |
| Grok 4.6 | xAI | $2 / $6 per 1M tokens | 200K | 7 | Aug 2026 |
| Claude Opus 5 | Anthropic | $5 / $25 per 1M tokens | 1M | 9 | Jul 2026 |
| Claude Sonnet 5 | Anthropic | $2 / $10 per 1M tokens | 1M | 9 | Jun 2026 |
| Mistral Ocr 4.0 | Mistral AI | – | – | 2 | Jun 2026 |
| Claude Fable 5 | Anthropic | $10 / $50 per 1M tokens | 1M | 9 | Jun 2026 |
| Claude Opus 4.8 | Anthropic | $5 / $25 per 1M tokens | 1M | 8 | Jun 2026 |
| DeepSeek V4 Flash | DeepSeek | $0.19 / $0.51 per 1M tokens | 1M | 22 | Jun 2026 |
| DeepSeek V4 Pro | DeepSeek | $1.74 / $3.48 per 1M tokens | 1M | 17 | Jun 2026 |
| Kimi K2.7 Code | Moonshot AI | $0.95 / $4 per 1M tokens | 256K | 14 | Jun 2026 |
| Mai Image 2.5 | – | $0.048 per image | 32K | 1 | Jun 2026 |
| Mai Image 2.5 Flash | – | $0.02 per image | 32K | 1 | Jun 2026 |
| Mistral Medium 3.5 | Mistral AI | $1.50 / $7.50 per 1M tokens | 128K | 2 | Jun 2026 |
| Grok 4.20 Non Reasoning | xAI | $1.25 / $2.50 per 1M tokens | 262K | 5 | May 2026 |
| Grok 4.20 Reasoning | xAI | $1.25 / $2.50 per 1M tokens | 262K | 5 | May 2026 |
| Grok 4.3 | xAI | $1.25 / $2.50 per 1M tokens | 200K | 5 | May 2026 |
| Claude Opus 4.7 | Anthropic | $5 / $25 per 1M tokens | 1M | 7 | Apr 2026 |
| GPT Image 2 | OpenAI | $5 per 1M input tokens | – | 5 | Apr 2026 |
| GPT-5.5 | OpenAI | $5 / $30 per 1M tokens | 922K | 10 | Apr 2026 |
| Kimi K2.6 | Moonshot AI | $0.95 / $4 per 1M tokens | 256K | 13 | Apr 2026 |
| GPT-5.4 | OpenAI | $2.50 / $15 per 1M tokens | 922K | 9 | Mar 2026 |
| GPT-5.4 Mini | OpenAI | $0.75 / $4.50 per 1M tokens | 272K | 7 | Mar 2026 |
| GPT-5.4 Nano | OpenAI | $0.20 / $1.25 per 1M tokens | 272K | 6 | Mar 2026 |
| GPT-5.4 Pro | OpenAI | $30 / $180 per 1M tokens | 922K | 4 | Mar 2026 |
| Claude Opus 4.6 | Anthropic | $5 / $25 per 1M tokens | 1M | 7 | Feb 2026 |
| Claude Sonnet 4.6 | Anthropic | $3 / $15 per 1M tokens | 1M | 8 | Feb 2026 |
| Kimi K2.5 | Moonshot AI | $0.60 / $3 per 1M tokens | 256K | 8 | Feb 2026 |
| Model Router | – | $0.14 / $0 per 1M tokens | 200K | 2 | Feb 2026 |
| Flux.2 Pro | Black Forest Labs | $0.04 per image | 32K | 1 | Jan 2026 |
| Cohere Rerank V4.0 Fast | – | $0 per 1M input tokens | 32K | 1 | Dec 2025 |
| Cohere Rerank V4.0 Pro | – | $0 per 1M input tokens | 32K | 1 | Dec 2025 |
| DeepSeek V3.2 | DeepSeek | $0.58 / $1.68 per 1M tokens | 128K | 10 | Dec 2025 |
| DeepSeek V3.2 Speciale | DeepSeek | $0.58 / $1.68 per 1M tokens | 128K | 1 | Dec 2025 |
| Mistral Large 3 | Mistral AI | $0.50 / $1.50 per 1M tokens | 256K | 3 | Dec 2025 |
| Claude Opus 4.5 | Anthropic | $5 / $25 per 1M tokens | 200K | 8 | Nov 2025 |
| Grok 4.1 Fast Non Reasoning | xAI | $0.20 / $0.50 per 1M tokens | 128K | 3 | Nov 2025 |
| Grok 4.1 Fast Reasoning | xAI | $0.20 / $0.50 per 1M tokens | 128K | 2 | Nov 2025 |
| Kimi K2 Thinking | Moonshot AI | $0.60 / $2.50 per 1M tokens | 256K | 9 | Nov 2025 |
| Prebuilt Document | – | – | – | 1 | Nov 2025 |
| Prebuilt Layout | – | – | – | 1 | Nov 2025 |
| Prebuilt Read | – | – | – | 1 | Nov 2025 |
| Claude Haiku 4.5 | Anthropic | $1 / $5 per 1M tokens | 200K | 12 | Oct 2025 |
| Claude Sonnet 4.5 | Anthropic | $3 / $15 per 1M tokens | 200K | 9 | Oct 2025 |
| Mistral Document AI | Mistral AI | – | – | 1 | Oct 2025 |
| Mistral Ocr | Mistral AI | – | – | 3 | Oct 2025 |
| Phi 4 Mini Reasoning | Microsoft | $0.075 / $0.30 per 1M tokens | 128K | 1 | Oct 2025 |
| Phi 4 Reasoning | Microsoft | $0.125 / $0.50 per 1M tokens | 32K | 1 | Oct 2025 |
| Grok 4 Fast Non Reasoning | xAI | $0.20 / $0.50 per 1M tokens | – | 1 | Sep 2025 |
| Grok 4 Fast Reasoning | xAI | $0.20 / $0.50 per 1M tokens | – | 1 | Sep 2025 |
| Grok Code Fast 1 | xAI | $0.20 / $1.50 per 1M tokens | 256K | 3 | Sep 2025 |
| DeepSeek V3.1 | DeepSeek | $1.23 / $4.94 per 1M tokens | 160K | 12 | Aug 2025 |
| FLUX 1.1 Pro | Black Forest Labs | $0.04 per image | 5K | 1 | Aug 2025 |
| Flux.1 Kontext Pro | Black Forest Labs | $0.04 per image | 5K | 1 | Aug 2025 |
| GPT OSS 120B | OpenAI | $0.15 / $0.60 per 1M tokens | 128K | 22 | Aug 2025 |
| Grok 4 | xAI | $3 / $15 per 1M tokens | 262K | 4 | Jul 2025 |
| Jais 30B Chat | – | $3,200 / $9,710 per 1M tokens | 8K | 1 | Jul 2025 |
| Mai Ds R1 | – | $1.35 / $5.40 per 1M tokens | 128K | 1 | Jul 2025 |
| Codex Mini | OpenAI | $1.50 / $6 per 1M tokens | 200K | 2 | Jun 2025 |
| Grok 3 Mini | xAI | $0.25 / $1.27 per 1M tokens | 128K | 3 | Jun 2025 |
| Whisper | OpenAI | $0.0001 per second | – | 4 | Jun 2025 |
| Embed V4.0 | Cohere | $0.12 per 1M tokens | 128K | 4 | May 2025 |
| Grok 3 | xAI | $3 / $15 per 1M tokens | 128K | 3 | May 2025 |
| Llama 4 Maverick 17B 128e Instruct | Meta | $0.25 / $1 per 1M tokens | 1M | 9 | Apr 2025 |
| Llama 4 Scout 17B 16e Instruct | Meta | $0.20 / $0.78 per 1M tokens | 10M | 10 | Apr 2025 |
| Phi 4 Mini Instruct | Microsoft | $0.075 / $0.30 per 1M tokens | 128K | 1 | Mar 2025 |
| Phi 4 Multimodal Instruct | Microsoft | $0.08 / $0.32 per 1M tokens | 128K | 1 | Mar 2025 |
| Phi 4 | Microsoft | $0.125 / $0.50 per 1M tokens | 16K | 2 | Feb 2025 |
| DeepSeek R1 | DeepSeek | $1.35 / $5.40 per 1M tokens | 64K | 16 | Jan 2025 |
| DeepSeek V3 | DeepSeek | $1.14 / $4.56 per 1M tokens | 128K | 15 | Jan 2025 |
| Llama 3.3 70B Instruct | Meta | $0.71 / $0.71 per 1M tokens | 128K | 18 | Dec 2024 |
| Ministral 3B | Mistral AI | $0.04 / $0.04 per 1M tokens | 128K | 3 | Nov 2024 |
| Phi 3 Medium 128K Instruct | Microsoft | $0.17 / $0.68 per 1M tokens | 128K | 1 | Nov 2024 |
| Phi 3 Medium 4K Instruct | Microsoft | $0.17 / $0.68 per 1M tokens | 4K | 1 | Nov 2024 |
| Phi 3 Mini 128K Instruct | Microsoft | $0.13 / $0.52 per 1M tokens | 128K | 2 | Nov 2024 |
| Phi 3 Mini 4K Instruct | Microsoft | $0.13 / $0.52 per 1M tokens | 4K | 1 | Nov 2024 |
| Phi 3 Small 128K Instruct | Microsoft | $0.15 / $0.60 per 1M tokens | 128K | 1 | Nov 2024 |
| Phi 3 Small 8K Instruct | Microsoft | $0.15 / $0.60 per 1M tokens | 8K | 1 | Nov 2024 |
| Phi 3.5 Mini Instruct | Microsoft | $0.13 / $0.52 per 1M tokens | 128K | 1 | Nov 2024 |
| Phi 3.5 MoE Instruct | Microsoft | $0.16 / $0.64 per 1M tokens | 128K | 1 | Nov 2024 |
| Phi 3.5 Vision Instruct | Microsoft | $0.13 / $0.52 per 1M tokens | 128K | 1 | Nov 2024 |
| Cohere Embed V3 English | – | $0.10 per 1M tokens | 512 | 1 | Oct 2024 |
| Cohere Embed V3 Multilingual | – | $0.10 per 1M tokens | 512 | 1 | Oct 2024 |
| Cohere Rerank V3 English | – | $0 per 1M input tokens | 4K | 1 | Oct 2024 |
| Cohere Rerank V3 Multilingual | – | $0 per 1M input tokens | 4K | 1 | Oct 2024 |
| Jamba Instruct | AI21 Labs | $0.50 / $0.70 per 1M tokens | 70K | 3 | Jul 2024 |
| Llama 3.1 70B Instruct | Meta | $2.68 / $3.54 per 1M tokens | 128K | 11 | Jul 2024 |
| Mistral Nemo | Mistral AI | $0.15 / $0.15 per 1M tokens | 128K | 3 | Jul 2024 |
| Codestral | Mistral AI | $0.30 / $0.90 per 1M tokens | 256K | 6 | Jun 2024 |
| Llama3 70B Instruct | Meta | $1.10 / $0.37 per 1M tokens | 8K | 7 | Apr 2024 |
| Mistral Large | Mistral AI | $2 / $6 per 1M tokens | 128K | 8 | Feb 2024 |
| Mistral Medium | Mistral AI | $0.40 / $2 per 1M tokens | 128K | 3 | Dec 2023 |
| Mistral Small | Mistral AI | $0.10 / $0.30 per 1M tokens | 128K | 6 | Dec 2023 |
| Claude Haiku 5.5 | Anthropic | $0.10 / $0.50 per 1M tokens | 1M | 7 | – |
