# Azure AI Foundry (/docs/providers/azure)


[Azure AI Foundry](https://azure.microsoft.com/en-us/products/ai-foundry) provides access to a wide range of AI models including OpenAI GPT series, Meta Llama, Mistral, and more, with enterprise-grade security and compliance.

Supported Models [#supported-models]

Azure AI Foundry hosts models from multiple providers:

| Provider | Models                 |
| -------- | ---------------------- |
| OpenAI   | GPT-4, GPT-4o, GPT-3.5 |
| Meta     | Llama series           |
| Mistral  | Mistral, Mixtral       |
| Cohere   | Command series         |
| AI21     | Jurassic series        |

Use the [Models API](/docs/models-api) to discover all available models.

Endpoint Format [#endpoint-format]

Chat Completions [#chat-completions]

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="model-id",
    messages=[{"role": "user", "content": "Hello!"}]
)
```

Authentication [#authentication]

Azure uses API keys or Microsoft Entra ID (Azure AD) tokens. Yunxin handles the authentication translation automatically.

Features [#features]

* **Enterprise Security** — SOC, HIPAA, and other compliance certifications
* **Regional Deployment** — Choose Azure regions for data residency
* **Content Filtering** — Built-in content safety filters
* **Private Endpoints** — VNET integration for private access

API Compatibility [#api-compatibility]

| Feature          | Support           |
| ---------------- | ----------------- |
| Chat Completions | ✓                 |
| Streaming        | ✓                 |
| Embeddings       | ✓                 |
| Vision           | ✓                 |
| Function Calling | ✓                 |
| Reasoning        | ✓ (select models) |

<Callout type="info">
  Azure AI Foundry models are accessed through Yunxin's unified API. Check the [Models API](/docs/models-api) for available models and their capabilities.
</Callout>