Billing-grade Claude Code cost tracking, in your terminal. Free & open source (MIT). Independent — not affiliated with Anthropic. npx wtclaude setup
Open Source
Joined June 2026
- Tweets49
- Following14
- Followers11
- Likes23
Pinned Tweet
Your Claude Code cost tracker is probably wrong.
Most read session logs. Logs don't carry billing-grade cost — so the number drifts from your actual bill.
WTClaude reads the statusline instead: the same source behind your bill.
It's free + open source. Here's what it does 🧵
Update: both Claude cliffs just moved — again. Anthropic extended BOTH the Fable 5 free window AND the +50% Claude Code weekly-limit boost to July 19 (both were closing this week).
From July 20, Fable moves to usage credits at $10/$50. That's two extensions in a week — the dates keep slipping, we just track the real ones: wtclaude.com/blog/state-of-c…
Work across two machines? Your Claude Code spend is scattered across both. WTClaude gives you one true total — billing-grade in the terminal, synced (opt-in) to a web dashboard.
See it: wtclaude.com/features?utm_so…
The honest test for any Claude Code cost tracker: run wtclaude compare and see your billing-grade number next to the log-based estimate. The gap is usually bigger than people expect.
The +50% Claude Code weekly-limit boost from May is set to expire July 13 (unless Anthropic extends it). Usage change, not a price change — but a third less weekly headroom if it lapses.
wtclaude limit shows where you stand against your plan limit, live: wtclaude.com/blog/claude-cod…
Model prices change, allowances expire, tokenizers differ — but the anchor doesn't move: WTClaude reads the same cost number Anthropic's own statusline computes for your terminal Claude Code. Not a reconstruction from logs.
See your real number: wtclaude.com/compare?utm_sou…
Update: Anthropic extended the free Fable 5 window. After backlash over the July-7 cutoff, included Fable access (up to 50% of your weekly limit on Pro/Max/Team/premium Enterprise) now runs through July 12 — then it's usage credits at $10/$50 per M.
One catch: if credits aren't enabled before the window closes, Fable access just stops — no grace period. See what your Fable pace would cost as credits (labeled estimate): wtclaude fable · wtclaude.com/blog/claude-cod…
Two Claude usage changes are getting mixed up — the clean version:
• Claude Cowork's 2× 5-hour usage promo was just extended to Aug 5 (Pro/Max/Team + legacy seat Enterprise; Cowork only).
• The Claude Code +50% WEEKLY-limit boost is a separate thing — still set to lapse July 13.
Different products, different limits. WTClaude shows where you stand on each: wtclaude.com/features?utm_so…
Today's the Fable 5 clock: the included allowance (up to 50% of your weekly limit) ends — Fable now bills as usage credits at $10/$50 per M. An allowance cliff, not a price you opted into.
What would your Fable usage cost as credits? (labeled estimate) wtclaude fable · wtclaude.com/blog/claude-cod…
Heads-up: Fable 5's included allowance (up to 50% of your weekly limit) ends TOMORROW (July 7) — after that, Fable bills as usage credits at $10/$50 per M. An allowance cliff, not a price you opt into.
See what your Fable pace would cost as credits (labeled estimate): wtclaude fable · wtclaude.com/blog/claude-cod…
Reminder: most Claude Code cost trackers read the session logs, which were never the billing source — so their numbers drift. WTClaude reads the statusline, the same source behind your bill. That's the whole difference.
New + free in wtclaude: waste. It reads your cache-read context waste — the tokens you re-send every turn that you don't need to — and shows where it's leaking. Read-only, billing-grade, nothing touched on your account.
npx wtclaude@latest → wtclaude waste : wtclaude.com/features?utm_so…
New in wtclaude: compare-models. It takes your own recorded, billing-grade usage and re-prices this month across Opus 4.8, Sonnet 5, and Fable 5 — split by surface (Code billing-grade, Cowork estimate, Chat excluded).
See what you'd actually pay on each: wtclaude.com/compare?utm_sou…
The whole idea behind WTClaude: you should see the same cost number Anthropic's own statusline computes for your terminal Claude Code — not a reconstruction from logs. Everything else (forecasts, cross-model, Cowork) is labeled an estimate, so you always know which numbers are solid. Independent, free, open source.
Sonnet 5 is cheaper per token than Opus — but read the asterisk: its tokenizer emits ~30% more tokens for the same work, so the real saving is smaller than the rate card. It's a real option, not a guarantee.
Price it on your own usage: wtclaude.com/compare?utm_sou…
Sonnet 5 (the new default), Opus 4.8, or Fable 5 (back, on a July-7 clock)? Three prices, three billing rules, and a tokenizer wrinkle that makes the sticker price misleading.
The honest, cost-first way to choose — priced from your own usage: wtclaude.com/blog/claude-cod…
WTClaude retweeted
Claude Fable 5 will be available again globally tomorrow.
After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests.
We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort.
Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research.
Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again.
Read our full blog: anthropic.com/news/redeployi…
Heads up: Claude Code's +50% weekly limits are set to expire July 13 (unless extended). Prices aren't changing — your weekly headroom is.
wtclaude limit shows how close you are to your plan limit, reading Anthropic's own rate-limit data — so a tighter ceiling shows up as a number you can see, not a wall you hit.
What changes + how to check: wtclaude.com/blog/claude-cod…
The most complete view of your Claude Code spend: billing-grade cost in the terminal, the compare reveal, one true total across machines, and a full dashboard.
See it: wtclaude.com/features?utm_so…
A few days left on Peerlist Launchpad — voting closes Sunday.
WTClaude: free, open-source, billing-grade Claude Code cost tracking. A look + a vote helps a lot: peerlist.io/beannationdefi/p…
