● runs in your browser
26% of AI spend is wasted. Most of it is one broken line.

Your prompt cache is probably broken.
Here's the line doing it.

Paste your system prompt. We find the timestamp, the request ID or the mutable memory block that's silently re-billing your cached prefix at full input price — and put a dollar figure on it.

Your prompt prefix

⌘/Ctrl + Enter

Verdict

grade

Waiting for a prompt

Paste a system prompt on the left. Nothing is uploaded — the audit runs in this tab.

hit rate
if fixed
waste / mo
waste / yr

Findings

0
No audit yet.

Cost model

Run an audit to model the cost.

What it checks for

Prefix caching is an exact-prefix match. The first changed byte kills the cache for everything after it, and no provider raises an error when that happens. These are the patterns that break it in production.

Gate it in CI, so it never ships again

A one-off audit finds today's bug. The bug comes back the next time someone adds a timestamp "for context freshness". prefix-audit runs in your pipeline and fails the PR that breaks the prefix — before the invoice explains it three weeks later.

name: prompt-cache
on: [pull_request]
jobs:
  audit:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with: { node-version: 20 }
      - run: npx prefix-audit prompts/support.md \
             --provider anthropic \
             --requests 8000 \
             --fail-on critical \
             --max-waste 500
exit 1

Fails the build

Any critical finding, or modelled waste above your threshold, turns the check red.

--baseline

Catches silent drift

Hashes the prefix and fails when it changes, so a one-character edit can't quietly cold-start every cache.

--stability

Proves it byte-stable

Diffs N real renders of the same prefix and points at the exact byte where they diverge.

The auditor is free. The gate is not.

The web tool costs nothing and always will. If you want the prefix to stay fixed across a team and a deploy schedule, that's the paid part.

$0 / forever

Web auditor + CLI

Unlimited audits, all 14 rules, the cost model, auto-fix, and the open-source CLI for local use. No account, no upload, no key.

$29 / month

CI gate

Hosted GitHub Action, baseline drift detection, PR comments naming the offending line, and Slack alerts when a deploy drops your hit rate.

$199 / month

Team + live monitoring

Ingest cache_read_input_tokens from your provider, chart real hit rate per feature, and alert on a 10-point drop in a rolling 24h window.

Sources for the numbers on this page: Harness State of AI in FinOps 2026 (26% of AI spend wasted, 72% hit a surprise AI bill); FinOps Foundation State of FinOps 2026 (98% now manage AI spend, up from 31% two years ago); ProjectDiscovery's engineering writeup (7% → 84% cache hit rate, 59% cost reduction, 9.8B tokens served from cache). Provider cache multipliers are transcribed from public 2026 price tables and are editable above — always verify against your own invoice.

Copied