Agent with Output Model

This example demonstrates how to use the output_model parameter to specify a different model for generating the final response, enabling model switching during agent execution.

Code

output_model.py

"""
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 OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=OpenAIChat(id="gpt-4.1"),
    output_model=OpenAIChat(id="gpt-5-mini"),
    tools=[DuckDuckGoTools()],
)

agent.print_response("Latest news from France?", stream=True)

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install libraries

   pip install -U agno openai ddgs
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch output_model.py
   
5. Run Agent

   Mac

   python output_model.py
   
6. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub