Prompt Caching

Prompt caching can help reduce processing time and costs. Consider it if you are using the same prompt multiple times in any flow.

You can read more about prompt caching with Anthropic models here.

Cache the system prompt

To use prompt caching in your Agno setup, pass the cache_system_prompt argument when initializing the Claude model:

from agno.agent import Agent
from agno.models.anthropic import Claude

agent = Agent(
    model=Claude(
        id="claude-sonnet-4-5-20250929",
        cache_system_prompt=True,
    ),
)

Notice that for prompt caching to work, the prompt needs to be of a certain length. You can read more about this on Anthropic's docs.

Extended cache

Set extended_cache_time=True for a one-hour cache TTL instead of five minutes. One-hour caching does not require a beta header:

from agno.agent import Agent
from agno.models.anthropic import Claude

agent = Agent(
    model=Claude(
        id="claude-sonnet-4-5-20250929",
        cache_system_prompt=True,
        extended_cache_time=True,
    ),
)

Multi-block caching with per-block TTL

Split the system prompt into independently-cacheable blocks with system_prompt_blocks. Each SystemPromptBlock controls its own cache flag and ttl. This lets you cache static instructions while leaving dynamic per-request content uncached.

from datetime import datetime

from agno.agent import Agent
from agno.models.anthropic import Claude, SystemPromptBlock

def get_system_prompt_blocks():
    return [
        # Static instructions, cached for 1 hour
        SystemPromptBlock(
            text="You are a senior software architect. Give concise, opinionated advice.",
            cache=True,
            ttl="1h",
        ),
        # Dynamic per-request context, never cached
        SystemPromptBlock(
            text=f"Current time: {datetime.now().isoformat()}",
            cache=False,
        ),
    ]

agent = Agent(
    model=Claude(
        id="claude-sonnet-4-5-20250929",
        cache_system_prompt=True,
        extended_cache_time=True,
        system_prompt_blocks=get_system_prompt_blocks,
    ),
    markdown=True,
)

Blocks are appended after the agent-built system message in the Anthropic system array. Pass a zero-argument callable to evaluate dynamic blocks on every request without reinstantiating the model. See Prompt Caching With a Dynamic Block.

`SystemPromptBlock` field	Type	Default	Description
`text`	`str`	required	The block content.
`cache`	`bool`	`True`	Add `cache_control` to this block. Independent of `cache_system_prompt`.
`ttl`	`Optional["5m" \| "1h"]`	`None`	Per-block TTL. Overrides the model-level `extended_cache_time` for this block.

Anthropic requires any 1h cached block to appear before any 5m block in the request. Since the agent-built block comes first and inherits the model-level TTL, set extended_cache_time=True whenever any SystemPromptBlock uses ttl="1h". Agno validates this ordering at assembly time and raises a clear error if it is violated.

Tool caching

Set cache_tools=True to cache tool definitions. Anthropic caches all tools as a prefix when cache_control is on the last tool.

agent = Agent(
    model=Claude(
        id="claude-sonnet-4-5-20250929",
        cache_tools=True,
    ),
    tools=[...],
)

Working example

prompt_caching.py

from pathlib import Path

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.utils.media import download_file

# 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-4-6",
        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}")

Usage

Set up your virtual environment

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

Set your API key

export ANTHROPIC_API_KEY=xxx

Install dependencies

uv pip install -U anthropic agno

Run Agent

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

python prompt_caching.py