> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenRouter

> Integrate with OpenRouter as a custom OpenAI-compatible AI Provider

Add your [OpenRouter](https://openrouter.ai/) endpoint to access 100+ models from OpenAI, Anthropic, Google, Meta, Mistral, and more in Arize AX's prompt playground and LLM-as-a-judge evaluations. OpenRouter exposes a single OpenAI-compatible endpoint, so it is added as a **Custom Model Endpoint** — Arize AX makes use of the OpenAI Client to make calls to it.

<Note>
  By adding this integration, your data may be sent through OpenRouter to the underlying model provider for certain actions within Arize AX (e.g., prompt playground) and your account may be billed for usage.
</Note>

## Add the Integration Using the Arize Skills

Add an OpenRouter integration from your coding agent using the [Arize Skills](/ax/agents/arize-skills):

<Prompt description="Create a custom model integration named 'my-openrouter' with my base URL https://openrouter.ai/api/v1 and API key sk-or-...">
  Create a custom model integration named 'my-openrouter' with my base URL [https://openrouter.ai/api/v1](https://openrouter.ai/api/v1) and API key sk-or-...
</Prompt>

## Add the Integration from Arize AX

### Select Custom Model Endpoints from the Providers List

<Frame caption="The AI Provider integrations tab">
  ![The AI Provider integrations tab](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ai-integration-providers-custom.png)
</Frame>

### Fill Out Your Integration Details

<Frame caption="The OpenRouter custom model integration configuration pane">
  ![The OpenRouter integration details pane](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ai-integration-providers-openrouter-integration-details.png)
</Frame>

Give your integration a name (e.g. `OpenRouter`). Then set your base URL and an [OpenRouter API key](https://openrouter.ai/keys) from the OpenRouter dashboard.

> Enter the base URL: `https://openrouter.ai/api/v1`. **Do not** include endpoint paths like `/chat/completions` as these are appended automatically.

If you need to send any extra headers to every request, set these.

You then need to define the available model deployments. Leave OpenAI default models off and add your OpenRouter model identifiers as custom model names. OpenRouter uses a `<provider>/<model>` format (e.g. `openai/gpt-4.1`, `anthropic/claude-sonnet-4-6`, `meta-llama/llama-3.3-70b-instruct`). See the [OpenRouter model catalog](https://openrouter.ai/models) for the full list of available identifiers.

### Advanced Settings

<Frame caption="The Advanced Settings configuration pane">
  ![The AI integration details tab](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ai-integration-providers-advanced-settings.png)
</Frame>

Expand the **Advanced Settings** section to configure the following:

* **Supports Function Calling** - Turn this on to allow the integration to use function calling features. This is on by default.
* **Authorized Orgs** - Configure which organizations have access to this integration.
* **Authorized Spaces** - Configure which spaces have access to this integration.

## Add the Integration

Finally check the box to agree to the terms and conditions, then select the **Add Integration** button to create the integration.