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

# Fallback Models: Callback Notification

> Use the ``callback`` parameter on FallbackConfig to get notified when a fallback model is activated.

Use the `callback` parameter on FallbackConfig to get notified when a fallback model is activated. This is useful for metrics, alerting, or logging which model actually served a request.

```python fallback_callback.py theme={null}
"""
Fallback Models — Callback Notification
==========================================

Use the ``callback`` parameter on FallbackConfig to get notified
when a fallback model is activated. This is useful for metrics,
alerting, or logging which model actually served a request.

The callback fires *after* the fallback model succeeds (including
after the full stream completes for streaming calls).
"""

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.models.fallback import FallbackConfig
from agno.models.openai import OpenAIChat


# ---------------------------------------------------------------------------
# Define a callback
# ---------------------------------------------------------------------------
def on_fallback(
    primary_model_id: str, fallback_model_id: str, error: Exception
) -> None:
    print(f"[fallback] {primary_model_id} -> {fallback_model_id} (reason: {error})")


# ---------------------------------------------------------------------------
# Create Agent with callback
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(id="gpt-4o", base_url="http://localhost:1/v1", retries=0),
    fallback_config=FallbackConfig(
        on_error=[Claude(id="claude-sonnet-4-20250514")],
        callback=on_fallback,
    ),
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("What is the meaning of life?", stream=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno anthropic openai
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `fallback_callback.py`, then run:

    ```bash theme={null}
    python fallback_callback.py
    ```
  </Step>
</Steps>

Full source: [cookbook/02\_agents/17\_fallback\_models/04\_fallback\_callback.py](https://github.com/agno-agi/agno/blob/main/cookbook/02_agents/17_fallback_models/04_fallback_callback.py)