Skip to main content
Use output_model to delegate final response generation to a different model. The primary model handles research, reasoning, and tool calls, then the output model formats the final response. Common use cases:
  • Cost optimization: Use a powerful model for complex tasks, a cheaper model for formatting
  • Specialized output: Use models optimized for different tasks (e.g., research vs. writing)
  • Cross-provider: Combine models from different providers

​
Code

output_model.py
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.hackernews import HackerNewsTools

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    output_model=OpenAIResponses(id="gpt-5.2"),
    output_model_prompt="Format the research findings as a concise executive summary with bullet points.",
    tools=[HackerNewsTools()],
)

agent.print_response("What are the top AI stories on HackerNews?", stream=True)
The primary model (gpt-5.2) researches HackerNews using tools, then the output model (gpt-4o) formats the findings according to the prompt.

​
Usage

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
2

Install dependencies

uv pip install -U agno openai
3

Export your OpenAI API key

export OPENAI_API_KEY="your_openai_api_key_here"
4

Run Agent

python output_model.py