Reasoning With Model

Use a separate native reasoning model (o1, o3, DeepSeek-R1, etc.) for thinking.

reasoning_with_model.py

"""
Reasoning With Model
=============================

Use a separate native reasoning model (o1, o3, DeepSeek-R1, etc.) for thinking.
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.6"),
    # Use a native reasoning model for the thinking step
    reasoning_model=OpenAIResponses(id="o3-mini"),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "A farmer has 17 sheep. All but 9 die. How many sheep are left?",
        stream=True,
        show_full_reasoning=True,
    )

Run the Example

1. Set up your virtual environment

   Mac

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

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

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

   Save the code above as reasoning_with_model.py, then run:

   python reasoning_with_model.py
   

Full source: cookbook/02_agents/13_reasoning/reasoning_with_model.py