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

# Prompt Caching

> Cache the system prompt with Claude on Vertex AI to reduce processing time and costs.

Use prompt caching with Claude on Vertex AI to cache the system prompt passed to the model.

```python prompt_caching.py theme={null}
"""
This cookbook shows how to use prompt caching with Agents using Anthropic models, to catch the system prompt passed to the model.

This can significantly reduce processing time and costs.
Use it when working with a static and large system prompt.

You can check more about prompt caching with Anthropic models here: https://docs.anthropic.com/en/docs/prompt-caching

Note: It takes a few seconds for the cache to be created and used for the second run.
"""

from pathlib import Path

from agno.agent import Agent
from agno.models.vertexai.claude import Claude
from agno.utils.media import download_file

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

# Load an example large system message from S3. A large prompt like this would benefit from caching.
txt_path = Path(__file__).parent.joinpath("system_prompt.txt")
download_file(
    "https://agno-public.s3.amazonaws.com/prompts/system_promt.txt",
    str(txt_path),
)
system_message = txt_path.read_text()

agent = Agent(
    model=Claude(
        id="claude-sonnet-4@20250514",
        cache_system_prompt=True,  # Activate prompt caching for Anthropic to cache the system prompt
    ),
    system_message=system_message,
    markdown=True,
)

# First run - this will create the cache
response = agent.run(
    "Explain the difference between REST and GraphQL APIs with examples"
)
if response and response.metrics:
    print(f"First run cache write tokens = {response.metrics.cache_write_tokens}")

# Second run - this will use the cached system prompt
response = agent.run(
    "What are the key principles of clean code and how do I apply them in Python?"
)
if response and response.metrics:
    print(f"Second run cache read tokens = {response.metrics.cache_read_tokens}")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno "anthropic[vertex]"
    ```
  </Step>

  <Step title="Export environment variables">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export ANTHROPIC_VERTEX_PROJECT_ID="your_anthropic_vertex_project_id_here"
      export CLOUD_ML_REGION="your_cloud_ml_region_here"
      ```

      ```bash Windows theme={null}
      $Env:ANTHROPIC_VERTEX_PROJECT_ID="your_anthropic_vertex_project_id_here"
      $Env:CLOUD_ML_REGION="your_cloud_ml_region_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Authenticate with Google Cloud">
    Sign in with Application Default Credentials:

    ```bash theme={null}
    gcloud auth application-default login
    ```
  </Step>

  <Step title="Run the example">
    Save the code above as `prompt_caching.py`, then run:

    ```bash theme={null}
    python prompt_caching.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/vertexai/claude/prompt\_caching.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/vertexai/claude/prompt_caching.py)