> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.boundaryml.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.boundaryml.com/_mcp/server.

# azure-openai

If you are using the new Microsoft Foundry (new) portal, please use: [`microsoft-foundry`](microsoft-foundry) instead.

For `azure-openai`, we provide a client that can be used to interact with the OpenAI API hosted on Azure using the `/chat/completions` endpoint.

Example:

```baml BAML
client<llm> MyClient {
  provider azure-openai
  options {
    resource_name "my-resource-name"
    deployment_id "my-deployment-id"
    // Alternatively, you can use the base_url field
    // base_url "https://my-resource-name.openai.azure.com/openai/deployments/my-deployment-id"
    api_version "2024-02-01"
    api_key env.AZURE_OPENAI_API_KEY
  }
}
```

`api_version` is required. Azure will return not found if the version is not specified.

The options are passed through directly to the API, barring a few. Here's a shorthand of the options:

## BAML-specific request `options`

These unique parameters (aka `options`) modify the API request sent to the provider.

You can use this to modify the azure api key, base url, and api version for example.

Will be injected via the header `API-KEY`. **Default: `env.AZURE_OPENAI_API_KEY`**

`API-KEY: $api_key`

The base URL for the API. **Default: `https://${resource_name}.openai.azure.com/openai/deployments/${deployment_id}`**

May be used instead of `resource_name` and `deployment_id`.

See the `base_url` field.

See the `base_url` field.

Will be passed via a query parameter `api-version`.

Additional headers to send with the request.

Example:

```baml BAML
client<llm> MyClient {
  provider azure-openai
  options {
    resource_name "my-resource-name"
    deployment_id "my-deployment-id"
    api_version "2024-02-01"
    api_key env.AZURE_OPENAI_API_KEY
    headers {
      "X-My-Header" "my-value"
    }
  }
}
```

The role to use if the role is not in the allowed\_roles. **Default: `"user"` usually, but some models like OpenAI's `gpt-5` will use `"system"`**

Picked the first role in `allowed_roles` if not "user", otherwise "user".

Which roles should we forward to the API? **Default: `["system", "user", "assistant"]` usually, but some models like OpenAI's `o1-mini` will use `["user", "assistant"]`**

When building prompts, any role not in this list will be set to the `default_role`.

A mapping to transform role names before sending to the API. **Default: `{}`** (no remapping)

For google-ai provider, the default is: `{ "assistant": "model" }`

This allows you to use standard role names in your prompts (like "user", "assistant", "system") but send different role names to the API. The remapping happens after role validation and default role assignment.

**Example:**

```json
{
  "user": "human",
  "assistant": "ai",
}
```

With this configuration, `{{ _.role("user") }}` in your prompt will result in a message with role "human" being sent to the API.

Which role metadata should we forward to the API? **Default: `[]`**

For example you can set this to `["foo", "bar"]` to forward the cache policy to the API.

If you do not set `allowed_role_metadata`, we will not forward any role metadata to the API even if it is set in the prompt.

Then in your prompt you can use something like:

```baml
client<llm> Foo {
  provider openai
  options {
    allowed_role_metadata: ["foo", "bar"]
  }
}

client<llm> FooWithout {
  provider openai
  options {
  }
}
template_string Foo() #"
  {{ _.role('user', foo={"type": "ephemeral"}, bar="1", cat=True) }}
  This will be have foo and bar, but not cat metadata. But only for Foo, not FooWithout.
  {{ _.role('user') }}
  This will have none of the role metadata for Foo or FooWithout.
"#
```

You can use the playground to see the raw curl request to see what is being sent to the API.

Whether the internal LLM client should use the streaming API. **Default: `true`**

Then in your prompt you can use something like:

```baml
client<llm> MyClientWithoutStreaming {
  provider anthropic
  options {
    model claude-3-5-haiku-20241022
    api_key env.ANTHROPIC_API_KEY
    max_tokens 1000
    supports_streaming false
  }
}

function MyFunction() -> string {
  client MyClientWithoutStreaming
  prompt #"Write a short story"#
}
```

```python
# This will be streamed from your python code perspective, 
# but under the hood it will call the non-streaming HTTP API
# and then return a streamable response with a single event
b.stream.MyFunction()

# This will work exactly the same as before
b.MyFunction()
```

Which finish reasons are allowed? **Default: `null`**

version 0.73.0 onwards: This is case insensitive.

Will raise a `BamlClientFinishReasonError` if the finish reason is not in the allow list. See [Exceptions](/guide/baml-basics/error-handling#bamlclientfinishreasonerror) for more details.

Note, only one of `finish_reason_allow_list` or `finish_reason_deny_list` can be set.

For example you can set this to `["stop"]` to only allow the stop finish reason, all other finish reasons (e.g. `length`) will treated as failures that PREVENT fallbacks and retries (similar to parsing errors).

Then in your code you can use something like:

```baml
client<llm> MyClient {
  provider "openai"
  options {
    model "gpt-5-mini"
    api_key env.OPENAI_API_KEY
    // Finish reason allow list will only allow the stop finish reason
    finish_reason_allow_list ["stop"]
  }
}
```

Which finish reasons are denied? **Default: `null`**

version 0.73.0 onwards: This is case insensitive.

Will raise a `BamlClientFinishReasonError` if the finish reason is in the deny list. See [Exceptions](/guide/baml-basics/error-handling#bamlclientfinishreasonerror) for more details.

Note, only one of `finish_reason_allow_list` or `finish_reason_deny_list` can be set.

For example you can set this to `["length"]` to stop the function from continuing if the finish reason is `length`. (e.g. LLM was cut off because it was too long).

Then in your code you can use something like:

```baml
client<llm> MyClient {
  provider "openai"
  options {
    model "gpt-5-mini"
    api_key env.OPENAI_API_KEY
    // Finish reason deny list will allow all finish reasons except length
    finish_reason_deny_list ["length"]
  }
}
```

Please let [us know on Discord](https://www.boundaryml.com/discord) if you have this use case! This is in alpha and we'd like to make sure we continue to cover your use cases.

The type of response to return from the client.

Sometimes you may expect a different response format than the provider default.
For example, using Azure you may be proxying to an endpoint that returns a different format than the OpenAI default.

**Default: `openai`**

### `media_url_handler`

Controls how media URLs are processed before sending to the provider. This allows you to override the default behavior for handling images, audio, PDFs, and videos.

```baml
client<llm> MyClient {
  provider openai
  options {
    media_url_handler {
      image "send_base64"                    // Options: send_base64 | send_url | send_url_add_mime_type | send_base64_unless_google_url
      audio "send_url"
      pdf "send_url_add_mime_type"
      video "send_url"
    }
  }
}
```

#### Options

Each media type can be configured with one of these modes:

* **`send_base64`** - Always download URLs and convert to base64 data URIs
* **`send_url`** - Pass URLs through unchanged to the provider
* **`send_url_add_mime_type`** - Ensure MIME type is present (may require downloading to detect)
* **`send_base64_unless_google_url`** - Only process non-gs\:// URLs (keep Google Cloud Storage URLs as-is)

#### Provider Defaults

If not specified, each provider uses these defaults:

| Provider     | Image                           | Audio                    | PDF           | Video      |
| ------------ | ------------------------------- | ------------------------ | ------------- | ---------- |
| OpenAI       | `send_url`                      | `send_base64`            | `send_url`    | `send_url` |
| Anthropic    | `send_url`                      | `send_url`               | `send_base64` | `send_url` |
| Google AI    | `send_base64_unless_google_url` | `send_url`               | `send_url`    | `send_url` |
| Vertex AI    | `send_url_add_mime_type`        | `send_url_add_mime_type` | `send_url`    | `send_url` |
| AWS Bedrock  | `send_base64`                   | `send_base64`            | `send_base64` | `send_url` |
| Azure OpenAI | `send_url`                      | `send_base64`            | `send_url`    | `send_url` |

#### When to Use

* **Use `send_base64`** when your provider doesn't support external URLs and you need to embed media content
* **Use `send_url`** when your provider handles URL fetching and you want to avoid the overhead of base64 conversion
* **Use `send_url_add_mime_type`** when your provider requires MIME type information (e.g., Vertex AI)
* **Use `send_base64_unless_google_url`** when working with Google Cloud Storage and want to preserve gs\:// URLs

URL fetching happens at request time and may add latency. Consider caching or pre-converting frequently used media when using `send_base64` mode.

## Provider request parameters

These are other `options` that are passed through to the provider, without modification by BAML. For example if the request has a `temperature` field, you can define it in the client here so every call has that set.

Consult the specific provider's documentation for more information.

For reasoning models (like `o1` or `o1-mini`), you must use `max_completion_tokens` instead of `max_tokens`.
Please set `max_tokens` to `null` in order to get this to work.

See the [OpenAI API documentation](https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_completion_tokens) and [OpenAI Reasoning Docs](https://platform.openai.com/docs/guides/reasoning#controlling-costs) for more details about token handling.

Example:

```baml BAML
client<llm> AzureO1 {
  provider azure-openai
  options {
    deployment_id "o1-mini"
    max_tokens null
  }
}
```

BAML will auto construct this field for you from the prompt

BAML will auto construct this field for you based on how you call the client in your code

For all other options, see the [official Azure API documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions).