Microsoft
Software giant whose MAI and Phi models cover text, voice and image
microsoft.comRedmond, United States
Microsoft is a US technology company headquartered in Redmond, Washington, founded in 1975 and listed on Nasdaq. In AI it trains the Phi small language models and, through Microsoft AI, the MAI voice and image models, and it hosts third-party models on the Azure AI Foundry platform.
- Founded
- 1975
- Type
- Public company
- Founders
- Bill Gates and Paul Allen
- AI lab
- Inference provider
- 120 hosted endpoints
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 Claude Fable 5 | azure | 1M | $10.00 | $50.00 | $1.00 | $12.50 | — |
| Claude Fable 5.1 | azure | 1M | $10.00 | $50.00 | $0.25 | $12.50 | 99.71% |
| Claude Fable 5.2 | azure | 1M | $8.00 | $40.00 | $0.20 | $10.00 | 100.00% |
| Claude Haiku 4.5 | azure/global | 200K | $1.00 | $5.00 | $0.10 | $1.25 | 100.00% |
| Claude Haiku 5.5 | azure/global | 1M | $0.10 | $0.50 | $0.01 | $0.125 | 100.00% |
| Claude Haiku 5.5 | azure/us | 1M | $0.11 | $0.55 | $0.011 | $0.1375 | 100.00% |
| Claude Opus 4.5 | azure/global | 200K | $5.00 | $25.00 | $0.50 | $6.25 | — |
| Claude Opus 4.6 | azure/global | 1M | $5.00 | $25.00 | $0.50 | $6.25 | — |
| Claude Opus 4.7 | azure/global | 1M | $5.00 | $25.00 | $0.50 | $6.25 | — |
| Claude Opus 4.8 | azure/global | 1M | $5.00 | $25.00 | $0.50 | $6.25 | — |
| Claude Opus 4.8 | azure/us | 1M | $5.50 | $27.50 | $0.55 | $6.875 | — |
| Claude Opus 5 | azure/global | 1M | $5.00 | $25.00 | $0.50 | $6.25 | 100.00% |
| Claude Opus 5 | azure/us | 1M | $5.50 | $27.50 | $0.55 | $6.875 | — |
| Claude Opus 5.5 | azure/global | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% |
| Claude Opus 5.5 | azure/us | 1M | $4.40 | $22.00 | $0.22 | $5.50 | — |
| Claude Sonnet 4.5 | azure/global | 200K | $3.00 | $15.00 | $0.30 | $3.75 | — |
| Claude Sonnet 4.6 | azure/global | 1M | $3.00 | $15.00 | $0.30 | $3.75 | 100.00% |
| Claude Sonnet 5 | azure/global | 1M | $2.00 | $10.00 | $0.20 | $2.50 | 100.00% |
| Claude Sonnet 5 | azure/us | 1M | $2.20 | $11.00 | $0.22 | $2.75 | — |
| Claude Sonnet 5.5 | azure/global | 1M | $2.00 | $10.00 | $0.10 | $2.50 | 100.00% |
| Claude Sonnet 5.5 | azure/us | 1M | $2.20 | $11.00 | $0.11 | $2.75 | 100.00% |
 DeepSeek V4 Flash 0423 | azure/us | 1M | $0.21 | $0.56 | $0.031 | — | 100.00% |
| DeepSeek V4 Pro 0423 | azure/us | 1M | $1.91 | $3.83 | $0.16 | — | 99.93% |
 GPT-3.5 Turbo (older v0613) | azure | 4K | $1.00 | $2.00 | — | — | 100.00% |
| GPT-3.5 Turbo 16k | azure | 16K | $3.00 | $4.00 | — | — | 100.00% |
| GPT-4 | azure | 8K | $30.00 | $60.00 | — | — | 100.00% |
| GPT-4.1 | azure | 1M | $2.00 | $8.00 | $0.50 | — | 100.00% |
| GPT-4.1 | azure/swedencentral | 1M | $2.20 | $8.80 | $0.55 | — | 100.00% |
| GPT-4.1 Mini | azure | 1M | $0.40 | $1.60 | $0.10 | — | 100.00% |
| GPT-4.1 Mini | azure/swedencentral | 1M | $0.44 | $1.76 | $0.11 | — | 100.00% |
| GPT-4.1 Nano | azure | 1M | $0.10 | $0.40 | $0.03 | — | 100.00% |
| GPT-4.1 Nano | azure/swedencentral | 1M | $0.11 | $0.44 | $0.033 | — | 100.00% |
| GPT-4o | azure | 128K | $2.50 | $10.00 | — | — | 100.00% |
| GPT-4o (2024-05-13) | azure | 128K | $5.00 | $15.00 | — | — | 100.00% |
| GPT-4o (2024-08-06) | azure | 128K | $2.50 | $10.00 | $1.25 | — | 100.00% |
| GPT-4o-mini | azure | 128K | $0.15 | $0.60 | $0.075 | — | 100.00% |
| GPT-4o-mini | azure/swedencentral | 128K | $0.165 | $0.66 | $0.0825 | — | 100.00% |
| GPT-5 | azure | 400K | $1.25 | $10.00 | $0.125 | — | 100.00% |
| GPT-5 | azure/swedencentral | 400K | $1.375 | $11.00 | $0.1375 | — | 100.00% |
| GPT-5 Mini | azure | 400K | $0.25 | $2.00 | $0.03 | — | 100.00% |
| GPT-5 Mini | azure/swedencentral | 400K | $0.275 | $2.20 | $0.033 | — | 100.00% |
| GPT-5 Nano | azure | 400K | $0.05 | $0.40 | $0.01 | — | 100.00% |
| GPT-5 Nano | azure/swedencentral | 400K | $0.055 | $0.44 | $0.011 | — | 100.00% |
| GPT-5.1 | azure | 400K | $1.25 | $10.00 | $0.13 | — | 100.00% |
| GPT-5.1 | azure/swedencentral | 400K | $1.375 | $11.00 | $0.143 | — | — |
| GPT-5.1-Codex | azure | 400K | $1.25 | $10.00 | $0.13 | — | 100.00% |
| GPT-5.1-Codex-Max | azure | 400K | $1.25 | $10.00 | $0.125 | — | 100.00% |
| GPT-5.1-Codex-Mini | azure | 400K | $0.25 | $2.00 | $0.03 | — | 10.25% |
| GPT-5.2 | azure | 400K | $1.75 | $14.00 | $0.175 | — | 100.00% |
| GPT-5.2 Chat | azure | 128K | $1.75 | $14.00 | $0.175 | — | — |
| GPT-5.2-Codex | azure | 400K | $1.75 | $14.00 | $0.175 | — | 100.00% |
| GPT-5.3-Codex | azure | 400K | $1.75 | $14.00 | $0.175 | — | 100.00% |
| GPT-5.4 | azure | 1.1M | $2.50 | $15.00 | $0.25 | — | 100.00% |
| GPT-5.4 | azure/eu | 1.1M | $2.75 | $16.50 | $0.275 | — | 100.00% |
| GPT-5.4 | azure/us | 1.1M | $2.75 | $16.50 | $0.275 | — | 100.00% |
| GPT-5.4 Mini | azure | 400K | $0.75 | $4.50 | $0.075 | — | 100.00% |
| GPT-5.4 Mini | azure/us | 400K | $0.825 | $4.95 | $0.0825 | — | 100.00% |
| GPT-5.4 Nano | azure | 400K | $0.20 | $1.25 | $0.02 | — | 99.93% |
| GPT-5.4 Nano | azure/us | 400K | $0.22 | $1.375 | $0.022 | — | 100.00% |
| GPT-5.4 Pro | azure | 1.1M | $30.00 | $180.00 | — | — | — |
| GPT-5.5 | azure | 1.1M | $5.00 | $30.00 | $0.50 | — | 100.00% |
| GPT-5.5 | azure/eu | 1.1M | $5.50 | $33.00 | $0.55 | — | 100.00% |
| GPT-5.5 | azure/us | 1.1M | $5.50 | $33.00 | $0.55 | — | 100.00% |
| GPT-5.6 Luna | azure | 1.1M | $0.20 | $1.20 | $0.02 | $0.25 | 100.00% |
| GPT-5.6 Luna | azure/eu | 1.1M | $0.22 | $1.32 | $0.022 | $0.275 | 100.00% |
| GPT-5.6 Luna | azure/us | 1.1M | $0.22 | $1.32 | $0.022 | $0.275 | 100.00% |
| GPT-5.6 Sol | azure | 1.1M | $4.00 | $20.00 | $0.40 | $5.00 | 100.00% |
| GPT-5.6 Sol | azure/eu | 1.1M | $4.40 | $22.00 | $0.44 | $5.50 | 100.00% |
| GPT-5.6 Sol | azure/us | 1.1M | $4.40 | $22.00 | $0.44 | $5.50 | 100.00% |
| GPT-5.6 Terra | azure | 1.1M | $2.00 | $12.00 | $0.20 | $2.50 | 100.00% |
| GPT-5.6 Terra | azure/eu | 1.1M | $2.20 | $13.20 | $0.22 | $2.75 | 100.00% |
| GPT-5.6 Terra | azure/us | 1.1M | $2.20 | $13.20 | $0.22 | $2.75 | 100.00% |
| GPT-6 Astra | azure | 1.1M | $10.00 | $50.00 | $1.00 | $12.50 | 97.00% |
| GPT-6 Astra | azure/us | 1.1M | $11.00 | $55.00 | $1.10 | $13.75 | 100.00% |
| GPT-6 Luna | azure | 1.1M | $0.10 | $0.50 | $0.01 | $0.125 | 100.00% |
| GPT-6 Luna | azure/eu | 1.1M | $0.11 | $0.55 | $0.011 | $0.1375 | 100.00% |
| GPT-6 Luna | azure/us | 1.1M | $0.11 | $0.55 | $0.011 | $0.1375 | 100.00% |
| GPT-6 Luna Decisions | azure | 1.1M | $0.10 | $0.00 | $0.00 | $0.00 | — |
| GPT-6 Sol | azure | 1.1M | $2.00 | $10.00 | $0.20 | $2.50 | 100.00% |
| GPT-6 Sol | azure/eu | 1.1M | $2.20 | $11.00 | $0.22 | $2.75 | 100.00% |
| GPT-6 Sol | azure/us | 1.1M | $2.20 | $11.00 | $0.22 | $2.75 | 100.00% |
| GPT-6.1 Sol | azure | 1.1M | $2.00 | $10.00 | $0.10 | $2.50 | 39.31% |
| GPT-6.1 Sol | azure/eu | 1.1M | $2.20 | $11.00 | $0.11 | $2.75 | 100.00% |
| GPT-6.1 Sol | azure/us | 1.1M | $2.20 | $11.00 | $0.11 | $2.75 | 100.00% |
| GPT-6.1 Terra | azure | 1.1M | $1.00 | $5.00 | $0.05 | $1.25 | 100.00% |
| GPT-6.1 Terra | azure/eu | 1.1M | $1.20 | $6.00 | $0.06 | $1.50 | 100.00% |
| GPT-6.1 Terra | azure/us | 1.1M | $1.10 | $5.50 | $0.055 | $1.375 | 100.00% |
| MAI-Image-2.5 | azure | 4K | $5.00 | $0.00 | — | — | 100.00% |
| MAI-Image-2.5 Pro | azure | 4K | $5.00 | $0.00 | — | — | 100.00% |
| MAI-Image-2.6 | azure | 4K | $5.00 | $0.00 | — | — | 100.00% |
| MAI-Image-2.6 Flash | azure | 4K | $1.75 | $0.00 | — | — | 100.00% |
| MAI-Transcribe 1.5 | azure | — | $360,000.00 | $0.00 | — | — | 100.00% |
| MAI-Transcribe 2 | azure | — | $100,000.00 | $0.00 | — | — | 100.00% |
| MAI-Voice-2 | azure | — | $22.00 | $0.00 | — | — | 100.00% |
| MAI-Voice-2-Flash | azure | — | $15.00 | $0.00 | — | — | 100.00% |
| MAI-Voice-2.1 | azure | — | $22.00 | $0.00 | — | — | 100.00% |
| MAI-Voice-2.1-Flash | azure | — | $15.00 | $0.00 | — | — | 100.00% |
| Microsoft-Decision-1 | azure | 33K | $0.042 | $0.00 | — | — | 100.00% |
| Text Embedding 3 Large | azure | 8K | $0.13 | $0.00 | — | — | 100.00% |
| Text Embedding 3 Small | azure | 8K | $0.02 | $0.00 | — | — | 100.00% |