# Set up Microsoft Foundry

Last validated Jun 8, 2026

\[Missing snippet: aperture\_release\_note.mdx]

Configure Microsoft Foundry in Aperture so your team can access OpenAI GPT and Anthropic Claude models deployed in Foundry through your tailnet. Foundry serves OpenAI models through an OpenAI-compatible `/openai` endpoint and Anthropic models through an Anthropic-compatible `/anthropic` endpoint. Because each endpoint uses a different API format, you configure each as its own provider in Aperture. The base URLs are specific to your Foundry resource and project, and the model names must match your Foundry deployment names.

\[Missing snippet: aperture\_any\_provider.mdx]

## Prerequisites

Before you begin, you need:

* An Aperture instance accessible from your device. Refer to [get started with Aperture][kb-aperture-get-started] if you have not set this up.
* A [Microsoft Foundry][xt-foundry-portal] resource and project with at least one model deployment.
* A [Foundry API key][xt-foundry-keys] for your resource.

## Configure the providers

Add Microsoft Foundry to your [Aperture configuration][kb-aperture-configuration]. Aperture's Foundry integration supports OpenAI GPT models and Anthropic Claude models, served through separate endpoints. Configure each endpoint as its own provider entry. Both base URLs are specific to your resource and project; find your resource and project names in the [Foundry portal][xt-foundry-portal]. Model names must match the deployment names in your Foundry project exactly.

### OpenAI GPT models

Configure Foundry's `/openai` endpoint to serve GPT models:

```json
{
  "providers": {
    "microsoft-foundry-openai": {
      "baseurl": "https://<your-resource>.services.ai.azure.com/api/projects/<your-project>/openai/",
      "apikey": "<your-foundry-api-key>",
      "name": "Microsoft Foundry (OpenAI)",
      "models": ["gpt-5.4", "gpt-5.4-mini", "gpt-5.4-nano", "gpt-5.3-codex"],
      "cost_basis": "azure",
      "compatibility": {
        "openai_chat": true,
        "openai_responses": true
      }
    }
  }
}
```

The configuration fields work as follows:

* **`baseurl`** intentionally ends with `/openai/`. Unlike most providers, where you supply only the API root, Foundry serves its OpenAI-compatible API under a project-scoped path. Aperture appends the incoming request path to this base, producing upstream URLs like `https://<your-resource>.services.ai.azure.com/api/projects/<your-project>/openai/v1/chat/completions`. Keep the trailing slash and do not strip the path segments.
* **`openai_responses`** enables the Responses API, which tools like OpenAI Codex use. When you include a `compatibility` block, set both flags explicitly. Without a compatibility block, Aperture enables only `openai_chat` by default.
* **`cost_basis`** is set to `azure` so Aperture prices requests using Azure OpenAI list prices instead of standard OpenAI prices. Use `azure-eu` for EU-region pricing. Set this field explicitly, because Aperture would otherwise infer `openai` pricing from the compatibility flags.

### Anthropic Claude models

Configure Foundry's `/anthropic` endpoint to serve Claude models as a second provider entry:

```json
{
  "providers": {
    "microsoft-foundry-anthropic": {
      "baseurl": "https://<your-resource>.services.ai.azure.com/api/projects/<your-project>/anthropic/",
      "apikey": "<your-foundry-api-key>",
      "name": "Microsoft Foundry (Anthropic)",
      "models": ["claude-sonnet-4-6", "claude-opus-4-8", "claude-haiku-4-5"],
      "cost_basis": "azure",
      "compatibility": {
        "anthropic_messages": true
      }
    }
  }
}
```

This entry differs from the OpenAI provider as follows:

* **`baseurl`** ends with `/anthropic/` instead of `/openai/`, pointing to Foundry's Anthropic-compatible endpoint. The same path-append behavior applies, so keep the trailing slash and do not strip the path segments.
* **`anthropic_messages`** tells Aperture to use the Anthropic Messages API format (`/v1/messages`) instead of the OpenAI chat completions format. Both providers use the same Foundry API key with the default `bearer` authorization.

Refer to the [provider compatibility reference][kb-provider-compatibility] for the full list of flags.

## Verify the provider

\[Missing snippet: aperture\_verify\_provider.mdx]

\[Missing snippet: aperture\_provider\_next\_steps.mdx]

[kb-aperture-configuration]: /docs/aperture/configuration

[kb-aperture-get-started]: /docs/aperture/get-started

[kb-provider-compatibility]: /docs/aperture/provider-compatibility

[xt-foundry-keys]: https://learn.microsoft.com/azure/ai-foundry/

[xt-foundry-portal]: https://ai.azure.com