Azure AI Foundry
Use open models like Llama, Qwen and gpt-oss alongside OpenAI's models through one managed Azure API.
Overview
Azure AI Foundry (now Microsoft Foundry) is Microsoft's platform for building with AI models. Models sold directly by Azure, including open-weight models such as Llama, Qwen and gpt-oss, run as fully managed deployments billed per million tokens. For steady, high-volume use you can buy Provisioned Throughput Units to reserve capacity.
Specifications
| Hosting type | Serverless API |
|---|---|
| Model families | Llama, Qwen, gpt-oss |
| LLM models | Llama 3.3 70B Instruct, Qwen3 32B, gpt-oss-120b, gpt-oss-20b |
| Pricing range | US$0.15 – US$1 |
| Pricing model | Pay per token, Reserved or committed capacity |
| Free tier available | No |
| Data center locations | United States, Canada, Brazil, Mexico, Ireland, Netherlands, United Kingdom, France, Germany, Switzerland, Norway, Sweden, Poland, Italy, Spain, Israel, Qatar, United Arab Emirates, South Africa, India, Japan, South Korea, Singapore, Hong Kong SAR China, Australia, Indonesia, Malaysia, New Zealand |
| Hardware / GPU options | Fully managed. Microsoft runs the models on its own GPU infrastructure; you don't choose hardware. |
| VRAM & memory | |
| Maximum model size | 400B |
| OpenAI-compatible API | Yes |
News about Microsoft Azure
All news →LLM Hosting Roundup: Anthropic’s capacity crunch, Vera Rubin and DeepSeek’s $15B (23 Oct 2026)
Anthropic's hunt for cloud capacity, NVIDIA's DSX POD and new Vera Rubin inference benchmarks, Dell's first Groq 3 rack, DeepSeek's reported $15B raise and Reflection's open-weights Beam model.
