Prompt Caching Extended

Set the extended-cache-ttl beta and extended_cache_time on Claude to hold the cached system prompt for one hour, and compare cache write and read tokens.

Extend caching time for agents using cache with Anthropic models.

Anthropic retired the source’s claude-sonnet-4-20250514 model on June 15, 2026. Replace it with claude-sonnet-4-6 before running. See Anthropic model deprecations.

prompt_caching_extended.py

"""
This cookbook shows how to extend caching time for agents using cache with Anthropic models.

You can check more about extended prompt caching with Anthropic models here: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#1-hour-cache-duration-beta
"""

from pathlib import Path

from agno.agent import Agent
from agno.models.anthropic 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_promt.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",
        betas=["extended-cache-ttl-2025-04-11"],
        system_prompt=system_message,
        cache_system_prompt=True,  # Activate prompt caching for Anthropic to cache the system prompt
        extended_cache_time=True,  # Extend the cache time from the default to 1 hour
    ),
    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

   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
   
3. Export your Anthropic API key

   Mac/Linux

   export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
   

   $Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
   
4. Update the Claude model

   Replace Claude(id="claude-sonnet-4-20250514") with Claude(id="claude-sonnet-4-6") in the saved file.

5. Run the example

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

   python prompt_caching_extended.py
   

Full source: cookbook/90_models/anthropic/prompt_caching_extended.py