Claude Code already logs every token it bills. claudebill reads those logs and shows cost per session, project, git branch, model, and day, plus what prompt caching saved you. Retroactive, offline, zero dependencies. npx claudebill.
Hi Product Hunt, Hassan here.
Every Claude Code session writes a transcript to ~/.claude with the exact token counts the API billed, split into fresh input, output, cache writes, and cache reads. Nobody reads them. I wanted to know which of my sessions burned the budget, whether prompt caching was actually earning its keep, and what my Max plan would have cost on the API.
So claudebill reads those transcripts. That is the whole trick:
- It is retroactive. It works on the history you already have, back to your first session. No hooks, nothing to install before you start.
- It never touches the network. Local files in, text out.
- It answers the questions that matter: cost per session, per project, per git branch (the closest thing to cost per PR), per model, per day, and a cache report that shows the sessions where caching fell apart.
- It works headless. Point it at a CI runner's Claude config dir and use --json or --csv.
- Every report is stamped with the price-table version, so a future price change can never quietly rewrite last month's number.
npx claudebill
It's MIT-licensed and a single dependency-free Node package. I'd love to hear which number you check first.
If your team wants a shared dashboard (per-engineer spend, budgets, Slack alerts), there is a waitlist issue on the repo: https://github.com/aitechexplore...
About claudebill on Product Hunt
“See what your Claude Code sessions actually cost”
claudebill launched on Product Hunt on September 18th, 2026 and earned 63 upvotes and 1 comments, placing #41 on the daily leaderboard. Claude Code already logs every token it bills. claudebill reads those logs and shows cost per session, project, git branch, model, and day, plus what prompt caching saved you. Retroactive, offline, zero dependencies. npx claudebill.
On the analytics side, claudebill competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how claudebill performed against the three products that launched closest to it on the same day.
Who hunted claudebill?
claudebill was hunted by Fakhar ul Hassan. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of claudebill including community comment highlights and product details, visit the product overview.
Fakhar ul Hassan