Skip to main content

​
Code

Set reasoning_effort to "high" or "max" for deeper reasoning on complex tasks. While thinking is active, temperature, top_p, presence_penalty and frequency_penalty are ignored by the API.
cookbook/90_models/deepseek/reasoning_effort.py
from agno.agent import Agent
from agno.models.deepseek import DeepSeek

agent = Agent(
    model=DeepSeek(id="deepseek-v4-pro", reasoning_effort="max"),
    markdown=True,
)

task = (
    "A farmer needs to cross a river with a fox, a chicken and a sack of grain. "
    "The boat only fits the farmer and one item. The fox cannot be left alone with "
    "the chicken, and the chicken cannot be left alone with the grain. "
    "Provide a step-by-step solution."
)

if __name__ == "__main__":
    agent.print_response(task, stream=True, show_full_reasoning=True)

​
Usage

1

Set up your virtual environment

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

Set your API key

export DEEPSEEK_API_KEY=xxx
3

Install dependencies

uv pip install -U openai agno
4

Run Agent

python cookbook/90_models/deepseek/reasoning_effort.py