> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-studio-tools-doc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenRouter Responses

Interact with OpenRouter models using the OpenAI Responses API. OpenRouter's Responses API (currently in beta) provides OpenAI-compatible access to multiple AI models through a unified interface.

## Requirements

Set the `OPENROUTER_API_KEY` environment variable:

```bash theme={null}
export OPENROUTER_API_KEY=your-api-key
```

## Key Features

* **Unified Interface**: Access multiple AI providers through a single API
* **Fallback Model Routing**: Automatically try alternative models if the primary fails
* **Stateless API**: Each request is independent (no server-side state persisted)
* **Reasoning Support**: Enable reasoning for supported models

## Parameters

| Parameter  | Type                  | Default                          | Description                                            |
| ---------- | --------------------- | -------------------------------- | ------------------------------------------------------ |
| `id`       | `str`                 | `"openai/gpt-oss-20b"`           | The ID of the OpenRouter model to use                  |
| `name`     | `str`                 | `"OpenRouterResponses"`          | The name of the model                                  |
| `provider` | `str`                 | `"OpenRouter"`                   | The provider of the model                              |
| `api_key`  | `Optional[str]`       | `None`                           | The API key (defaults to `OPENROUTER_API_KEY` env var) |
| `base_url` | `str`                 | `"https://openrouter.ai/api/v1"` | The base URL for the OpenRouter API                    |
| `models`   | `Optional[List[str]]` | `None`                           | List of fallback model IDs for automatic retry         |
| `store`    | `Optional[bool]`      | `False`                          | Whether to store responses                             |

## Usage

### Basic Usage

```python theme={null}
from agno.agent import Agent
from agno.models.openrouter import OpenRouterResponses

agent = Agent(
    model=OpenRouterResponses(id="openai/gpt-oss-20b"),
    markdown=True,
)

agent.print_response("Share a 2 sentence horror story")
```

### With Reasoning

```python theme={null}
from agno.agent import Agent
from agno.models.openrouter import OpenRouterResponses

agent = Agent(
    model=OpenRouterResponses(
        id="openai/gpt-oss-20b",
        reasoning={"enabled": True},
    ),
    markdown=True,
)

agent.print_response("Share a 2 sentence horror story")
```

### Fallback Model Routing

If the primary model fails due to rate limits, timeouts, or unavailability, OpenRouter automatically tries the fallback models in order:

```python theme={null}
from agno.agent import Agent
from agno.models.openrouter import OpenRouterResponses

agent = Agent(
    model=OpenRouterResponses(
        id="openai/gpt-oss-20b",
        models=[
            "openai/gpt-oss-20b",
            "openai/gpt-4o",
        ],
    ),
    markdown=True,
)

agent.print_response("Write a haiku about coding", stream=True)
```

## Developer Resources

* [OpenRouter Responses API Documentation](https://openrouter.ai/docs/api/reference/responses/overview)
* [OpenRouter Model Routing](https://openrouter.ai/docs/features/model-routing)
* [OpenRouter](/reference/models/openrouter) (Chat Completion API)