> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek Thinking Mode

> Enable or disable DeepSeek V4 thinking mode and inspect reasoning_content.

DeepSeek V4 returns `reasoning_content` with thinking mode enabled by default. Set `use_thinking=False` for a faster response.

```python thinking_mode.py theme={null}
"""
Deepseek Thinking Mode
======================

DeepSeek V4 models run with thinking mode enabled by default, so you get
reasoning_content out of the box. Use the `use_thinking` flag to control it:
`use_thinking=True` forces it on, `use_thinking=False` turns it off for a faster,
cheaper response.
"""

from agno.agent import Agent
from agno.models.deepseek import DeepSeek

# ---------------------------------------------------------------------------
# Thinking enabled (default) - returns reasoning_content
# ---------------------------------------------------------------------------

thinking_agent = Agent(model=DeepSeek(id="deepseek-v4-flash"), markdown=True)

# ---------------------------------------------------------------------------
# Thinking disabled - faster, no reasoning_content
# ---------------------------------------------------------------------------

non_thinking_agent = Agent(
    model=DeepSeek(id="deepseek-v4-flash", use_thinking=False),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agents
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    thinking_agent.print_response("Why is the sky blue?", stream=True)

    non_thinking_agent.print_response("Why is the sky blue?", stream=True)
```

## Run the Example

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

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai
```

**2. Export your DeepSeek API key**

```bash Mac/Linux theme={null}
export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
```

```bash Windows theme={null}
$Env:DEEPSEEK_API_KEY="your_deepseek_api_key_here"
```

**3. Run the example**

Save the code above as `thinking_mode.py`, then run:

```bash theme={null}
python thinking_mode.py
```

Full source: [cookbook/90\_models/deepseek/thinking\_mode.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/deepseek/thinking_mode.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.