prompt_caching.py
"""
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
1
Set up your virtual environment
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
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
prompt_caching.py, then run:python prompt_caching.py