> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Non-Reasoning Model Agent

This example demonstrates how it works when you pass a non-reasoning model as a reasoning model.
It defaults to using the default OpenAI reasoning model.
We recommend using the appropriate reasoning model or passing `reasoning=True` to use the default Chain-of-Thought reasoning.

## Code

```python cookbook/reasoning/agents/default_chain_of_thought.py theme={null}
from agno.agent import Agent
from agno.models.openai import OpenAIChat

reasoning_agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    reasoning_model=OpenAIChat(
        id="gpt-4o", max_tokens=1200
    ),  # Should default to manual COT because it is not a native reasoning model
    markdown=True,
)
reasoning_agent.print_response(
    "Give me steps to write a python script for fibonacci series",
    stream=True,
    show_full_reasoning=True,
)


# It uses the default model of the Agent
reasoning_agent = Agent(
    model=OpenAIChat(id="gpt-4o", max_tokens=1200),
    reasoning=True,
    markdown=True,
)
reasoning_agent.print_response(
    "Give me steps to write a python script for fibonacci series",
    stream=True,
    show_full_reasoning=True,
)


```

## Usage

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Set your API key">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

  <Step title="Install libraries">
    ```bash theme={null}
    pip install -U openai agno
    ```
  </Step>

  <Step title="Run Example">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/reasoning/agents/default_chain_of_thought.py
      ```

      ```bash Windows theme={null}
      python cookbook/reasoning/agents/default_chain_of_thought.py
      ```
    </CodeGroup>
  </Step>
</Steps>