# Azure Foundry

> Configure azurefoundry deployments and understand provider-specific behavior.

URL: https://boelabs.com/en/docs/ai-gateway/providers-azure-foundry
Language: English

## Configure a deployment

Send this body to `POST /admin/deployments` with an operator credential. Replace the example
credentials and choose a model available to your provider account. See
[Creating deployments](https://boelabs.com/docs/ai-gateway/creating-deployments) for the shared configuration fields.

```json
{
  "publicModel": "azure-deepseek",
  "adapterKey": "azurefoundry",
  "upstreamModel": "DeepSeek-V3.1",
  "credentials": { "apiKey": "...", "baseUrl": "https://my-foundry-resource.services.ai.azure.com" }
}
```

## Behavior and limitations

- **Credentials**: `apiKey`, `baseUrl`.
- Use this adapter — not [Azure OpenAI](https://boelabs.com/docs/ai-gateway/providers-azure-openai) — for models Azure itself sells
  through Foundry, such as `DeepSeek-V3.1` or `grok-4.3`. Their upstream transport is Chat Completions;
  AI Gateway still renders every public text contract (Chat Completions, Responses, Messages) over it.
- **Default transport**: Chat Completions for text. No native image/embedding transport.
- Two independent providers, two independent catalogs: a model available on both Azure OpenAI and Azure
  Foundry needs a separate catalog entry (and deployment) per adapter.
- Catalog: `src/adapters/azurefoundry/catalog.json`.

## Next steps

- [Azure OpenAI](https://boelabs.com/docs/ai-gateway/providers-azure-openai) — the other Azure adapter.
- [Creating deployments](https://boelabs.com/docs/ai-gateway/creating-deployments) — the full request shape.