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

# Output Model

> Use a separate output model to refine the main model's response.

```python output_model.py theme={null}
"""
Output Model
=============================

Use a separate output model to refine the main model's response.

The output_model receives the same conversation but generates its own
response, replacing the main model's output. This is useful when you
want a cheaper model to handle reasoning/tool-use and a more capable
model to produce the final polished answer.

For structured JSON output, use ``parser_model`` instead (see parser_model.py).
"""

from agno.agent import Agent, RunOutput
from agno.models.openai import OpenAIResponses
from rich.pretty import pprint

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5-mini"),
    description="You are a helpful chef that provides detailed recipe information.",
    output_model=OpenAIResponses(id="gpt-5.2"),
    output_model_prompt="You are a world-class culinary writer. Rewrite the recipe with vivid descriptions, pro tips, and elegant formatting.",
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    run: RunOutput = agent.run("Give me a recipe for pad thai.")
    pprint(run.content)
```

## Run the Example

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

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

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

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

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

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

Full source: [cookbook/02\_agents/02\_input\_output/output\_model.py](https://github.com/agno-agi/agno/blob/main/cookbook/02_agents/02_input_output/output_model.py)