Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
You are viewing v1 docs. For the latest documentation, visit docs.agno.com
Learn how to use OpenRouter with Agno.
OPENROUTER_API_KEY environment variable. Get your key from here.
export OPENROUTER_API_KEY=***
setx OPENROUTER_API_KEY ***
OpenRouter with your Agent:
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.")
| Parameter | Type | Default | Description |
|---|---|---|---|
id | str | "gpt-4o" | The specific model ID used for generating responses. |
name | str | "OpenRouter" | The name identifier for the OpenRouter agent. |
provider | str | "OpenRouter:"+id | The provider of the model, combining "OpenRouter" with the model ID. |
api_key | Optional[str] | - | The API key for authenticating requests to the OpenRouter service. Retrieved from the environment variable OPENROUTER_API_KEY. |
base_url | str | "https://openrouter.ai/api/v1" | The base URL for making API requests to the OpenRouter service. |
max_tokens | int | 1024 | The maximum number of tokens to generate in the response. |
OpenRouter also supports the params of OpenAI.
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.Was this page helpful?