> ## 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.

# Google Thinking Agent

> Solve a logic puzzle with a Gemini thinking budget and thought summaries enabled.

```python thinking_agent.py theme={null}
"""
Google Thinking Agent
=====================

Cookbook example for `google/gemini/thinking_agent.py`.
"""

from agno.agent import Agent
from agno.models.google import Gemini

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

task = (
    "Three missionaries and three cannibals need to cross a river. "
    "They have a boat that can carry up to two people at a time. "
    "If, at any time, the cannibals outnumber the missionaries on either side of the river, the cannibals will eat the missionaries. "
    "How can all six people get across the river safely? Provide a step-by-step solution and show the solutions as an ascii diagram"
)

agent = Agent(
    model=Gemini(
        id="gemini-2.5-pro",
        thinking_budget=1280,  # Enable thinking with token budget
        include_thoughts=True,  # Include thought summaries in response
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response(task)

    # --- Sync + Streaming ---
    agent.print_response(task, stream=True)
```

## Run the Example

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

**1. Install dependencies**

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

**2. Export your Google API key**

```bash Mac/Linux theme={null}
export GOOGLE_API_KEY="your_google_api_key_here"
```

```bash Windows theme={null}
$Env:GOOGLE_API_KEY="your_google_api_key_here"
```

**3. Run the example**

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

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

Full source: [cookbook/90\_models/google/gemini/thinking\_agent.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/google/gemini/thinking_agent.py)


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