> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenRouter

> Learn how to use OpenRouter with Agno.

OpenRouter is a platform for providing endpoints for Large Language models.

## Authentication

Set your `OPENROUTER_API_KEY` environment variable. Get your key from [here](https://openrouter.ai/settings/keys).

<CodeGroup>
  ```bash Mac theme={null}
  export OPENROUTER_API_KEY=***
  ```

  ```bash Windows theme={null}
  setx OPENROUTER_API_KEY ***
  ```
</CodeGroup>

## Example

Use `OpenRouter` with your `Agent`:

<CodeGroup>
  ```python agent.py theme={null}
  from agno.agent import Agent, RunResponse
  from agno.models.openrouter import OpenRouter

  agent = Agent(
      model=OpenRouter(id="gpt-4o"),
      markdown=True
  )

  # Print the response in the terminal
  agent.print_response("Share a 2 sentence horror story.")

  ```
</CodeGroup>

## Params

<Snippet file="model-openrouter-params.mdx" />

`OpenRouter` also supports the params of [OpenAI](/reference/models/openai).

## Prompt caching

Prompt caching will happen automatically using our `OpenRouter` model, when the used provider supports it. In other cases you can activate it via the `cache_control` header.
You can read more about prompt caching with OpenRouter in [their docs](https://openrouter.ai/docs/features/prompt-caching).