Skip to main content
cachemaxxing logo

cachemaxxing

PyPI Python CI License: MIT

Stop paying full price for the same tokens.

Anthropic, OpenAI and Gemini bill a repeated prompt prefix at a fraction of the input price, but only when the bytes really repeat. cachemaxxing finds where they don't, tells you what it costs, and lays your prompts out so they do. It is a thin library, not a proxy: zero runtime dependencies, and you keep your own SDK client.

  • Measure. usage() turns any provider's response into the same numbers: input, cache read, cache write, output, estimated $ and hit rate. cachemaxxing report totals them per call site.
  • Diagnose. cachemaxxing diff shows the first byte where two consecutive requests diverge, and why.
  • Fix. Prompt orders your prompt from most to least stable and places each provider's cache markers for you.
from cachemaxxing import Prompt, usage

p = Prompt(call_site="support.answer")
p.tools(TOOLS).system(SYSTEM).context(DOCS).history(messages).retrieved(chunks).user(question)

resp = client.messages.create(max_tokens=1024, **p.anthropic("claude-haiku-5-5"))

u = usage(resp)
print(f"{u.hit_rate:.0%} of input from cache, ~${u.est_cost or 0:.4f}")

Works with

How
Anthropic client.messages.create(**p.anthropic(model))
OpenAI client.responses.create(**p.openai(model)) or client.chat.completions.create(**p.openai_chat(model))
Gemini client.models.generate_content(**p.gemini(model)), with an explicit cache via gemini_cache() when should_cache() says it pays
LiteLLM litellm.completion(**p.litellm("anthropic/claude-haiku-5-5"))
LangChain agents create_agent(..., middleware=[CacheMiddleware("support.agent")])
LangGraph graphs, LCEL chains llm = CachedModel(chat_model, system=SYSTEM), then llm.invoke(state["messages"])

On OpenAI GPT-5.6+ it places explicit cache breakpoints. On Anthropic it places cache_control markers, at most 4. Gemini stays on implicit caching unless an explicit cache pays.

Find the misses

$ cachemaxxing report calls.jsonl --min-hit-rate 0.6     # from record() logs; exits 1 below the threshold
call site   calls  hit rate  input   cache read  cache write  output  est $   top drift
rag.answer  4      88.8%     31,574  28,024      714          2,601   0.0020

$ cachemaxxing diff request_1.json request_2.json
diverges at system[0].text char 41 (timestamp), after ~14 matching tokens
  a: 'You are helpful. Today is 2026-10-30T10:00:00Z.'
  b: 'You are helpful. Today is 2026-10-30T10:05:00Z.'

Benchmark

Cached input tokens per 8-turn chat, naive vs cachemaxxing

Provider Model Cached input $ per conversation Saving
Anthropic claude-haiku-5-5 0.0% → 94.8% $0.0092 → $0.0017 82%
OpenAI gpt-6-luna 0.0% → 93.1% $0.0070 → $0.0012 83%
Gemini gemini-3.8-flash 0.0% → 97.5% $0.0484 → $0.0094 80%

The same 8-turn conversation was run for 3 customers per arm, each starting from a cold cache. Costs are estimates at list price. The naive arm has four common habits: a timestamp at the top of the prompt, tool order that varies, JSON key order that varies, and history re-rendered every turn. The Gemini row uses an explicit cache, with its creation and storage cost included; with implicit caching alone it reached 40.0%. Data: benchmarks/results/, 2026-10-30.

Examples

Install

pip install cachemaxxing                  # or: uv add cachemaxxing
pip install "cachemaxxing[anthropic]"     # extras: anthropic, openai, gemini, litellm, langchain

Docs: https://ashhadahsan.github.io/cachemaxxing/ covers the quickstart, how caching works per provider, diagnosing a low hit rate, LangChain and LangGraph, the API reference, and how it compares.

MIT licensed.

Metadata

Release files for cachemaxxing 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cachemaxxing 0.2.0
File Size Uploaded Provenance Actions
cachemaxxing-0.2.0.tar.gz 21.4 kB With provenance Details for cachemaxxing-0.2.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for cachemaxxing 0.2.0
File Interpreter ABI Platform Actions
cachemaxxing-0.2.0-py3-none-any.whl Python 3 none any Details for cachemaxxing-0.2.0-py3-none-any.whl

Total release size: 46.6 kB

Release files / cachemaxxing-0.2.0.tar.gz

Download URL cachemaxxing-0.2.0.tar.gz
Size 21.4 kB
Tags Source
SHA-256 checksum
How to use checksums
a8c35b364632983d1917da027154c3d86ded1c4b3d037f565f4031e7a3dd67bc
BLAKE2b-256 checksum
How to use checksums
1f9c8cbda5cc586699d70e2dd4ba8164aff2505d18bcec719d2fbcce28228c8a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / cachemaxxing-0.2.0-py3-none-any.whl

Download URL cachemaxxing-0.2.0-py3-none-any.whl
Size 25.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
46e8936b234e2b4a1630e6df4eaa13d876720a1889051cc014fd8831ffef9a96
BLAKE2b-256 checksum
How to use checksums
551856f65375cbaefa657104389119ba39fb259df3c33d3758cb7844f7bde13e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Security for cachemaxxing 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for cachemaxxing-0.2.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page