Vertex AI Thinking

Enable extended thinking with a 1024-token budget on Claude Sonnet 4 via Vertex AI.

thinking.py

"""
Vertexai Thinking
=================

Cookbook example for `vertexai/claude/thinking.py`.
"""

from agno.agent import Agent
from agno.models.vertexai.claude import Claude

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

agent = Agent(
    model=Claude(
        id="claude-sonnet-4@20250514",
        max_tokens=2048,
        thinking={"type": "enabled", "budget_tokens": 1024},
    ),
    markdown=True,
)

# Print the response in the terminal

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("Share a very scary 2 sentence horror story")

    # --- Sync + Streaming ---
    agent.print_response("Share a very scary 2 sentence horror story", stream=True)

Run the Example

1. Set up your virtual environment

   Mac

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

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno "anthropic[vertex]"
   
3. Export environment variables

   Mac/Linux

   export ANTHROPIC_VERTEX_PROJECT_ID="your_anthropic_vertex_project_id_here"
   export CLOUD_ML_REGION="your_cloud_ml_region_here"
   

   $Env:ANTHROPIC_VERTEX_PROJECT_ID="your_anthropic_vertex_project_id_here"
   $Env:CLOUD_ML_REGION="your_cloud_ml_region_here"
   
4. Authenticate with Google Cloud

   Sign in with Application Default Credentials:

   gcloud auth application-default login
   
5. Run the example

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

   python thinking.py
   

Full source: cookbook/90_models/vertexai/claude/thinking.py