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

# How to Configure OpenRouter with Gobi

<Tip>
  **Discover Inception models [here](https://hub.gourmand.dev/inceptionlabs)**
</Tip>

<Info>
  Get an API key from [OpenRouter](https://openrouter.ai/keys)
</Info>

<Tabs>
  <Tab title="YAML">
    ```yaml title="config.yaml" theme={null}
    models:
      - name: <MODEL_NAME>
        provider: openrouter
        model: <MODEL_ID>
        apiBase: https://openrouter.ai/api/v1
        apiKey: <YOUR_OPEN_ROUTER_API_KEY>
    ```
  </Tab>

  <Tab title="JSON (Deprecated)">
    ```json title="config.json" theme={null}
    {
      "models": [
        {
          "title": "<MODEL_NAME>",
          "provider": "openrouter",
          "model": "<MODEL_ID>",
          "apiBase": "https://openrouter.ai/api/v1",
          "apiKey": "<YOUR_OPEN_ROUTER_API_KEY>"
        }
      ]
    }
    ```
  </Tab>
</Tabs>

<Info>
  **Check out a more advanced configuration [here](https://hub.gourmand.dev/openrouter/qwen3-coder?view=config)**
</Info>

## Optional configuration

OpenRouter allows you configure provider preferences, model routing configuration, and more. You can set these via `requestOptions`.

For example, to prevent extra long prompts from being compressed, you can explicitly turn off [Transforms](https://openrouter.ai/docs/features/message-transforms):)

<Tabs>
  <Tab title="YAML">
    ```yaml title="config.yaml" theme={null}
    models:
      - name: <MODEL_NAME>
        provider: openrouter
        model: <MODEL_ID>
        requestOptions:
          extraBodyProperties:
            transforms: []
    ```
  </Tab>

  <Tab title="JSON (Deprecated)">
    ```json title="config.json" theme={null}
    {
      "models": [
        {
          "title": "<MODEL_NAME>",
          "provider": "openrouter",
          "model": "<MODEL_ID>",
          "requestOptions": {
            "extraBodyProperties": {
              "transforms": []
            }
          }
        }
      ]
    }
    ```
  </Tab>
</Tabs>

## Model Capabilities

OpenRouter models may require explicit capability configuration because the proxy doesn't always preserve the function calling support of the original model.

<Info>
  Gobi automatically uses system message tools for models that don't support
  native function calling, so Agent mode should work even without explicit
  capability configuration. However, you can still override capabilities if
  needed.
</Info>

If you're experiencing issues with Agent mode or tools not working, you can add the capabilities field:

<Tabs>
  <Tab title="YAML">
    ```yaml title="config.yaml" theme={null}
    models:
      - name: <MODEL_NAME>
        provider: openrouter
        model: <MODEL_ID>
        apiBase: https://openrouter.ai/api/v1
        apiKey: <YOUR_OPEN_ROUTER_API_KEY>
        capabilities:
          - tool_use      # Enable function calling for Agent mode
    ```
  </Tab>

  <Tab title="JSON (Deprecated)">
    ```json title="config.json" theme={null}
    {
      "models": [
        {
          "title": "<MODEL_NAME>",
          "provider": "openrouter",
          "model": "<MODEL_ID>",
          "apiBase": "https://openrouter.ai/api/v1",
          "apiKey": "<YOUR_OPEN_ROUTER_API_KEY>",
          "capabilities": {
            "tools": true, // Enable function calling for Agent mode
          }
        }
      ]
    }
    ```
  </Tab>
</Tabs>

<Note>
  Not all models support function calling. Check the [OpenRouter models page](https://openrouter.ai/models) for specific model capabilities.
</Note>