> ## 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.

# Output Schema

> This example shows how to use the output_model parameter to specify the model that will be used to generate the final response.

```python theme={null}
"""
Output Schema
=============================

This example shows how to use the output_model parameter to specify the model that will be used to generate the final response.
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    output_model=OpenAIResponses(id="gpt-5-mini"),
    tools=[WebSearchTools()],
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("Latest news from France?", stream=True)
```

## Run the Example

```bash theme={null}
# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/02_agents/02_input_output

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python output_schema.py
```