ccusage
Hacker ApprovedThe most recommended of 3 usage trackers
Free CLI that reads local Claude Code logs to show token usage and API-equivalent cost. Main caveat: slow, re-parses logs from scratch.
Free CLI that reads local Claude Code logs to show token usage and API-equivalent cost. Main caveat: slow, re-parses logs from scratch.
11 people gave an opinion
- recommend it
- 10
- criticize it
- 1
- approval share
- 91%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- 10 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Recommended as an established option
“great libraries already exist for usage tracking (like ccusage)”
Comment from 18 Feb 2026 in “Show HN: Strava for Claude Code” “There’s also the ccusage package that I find useful.”
Comment from 23 Jan 2026 in “I was banned from Claude for scaffolding a Claude.md file” “I second ccusage, it's nice”
Comment from 27 Jun 2026 in “DeepSeek open-sources inference optimizations with 60–85% faster generation [pdf]” Shows token usage and costs
“the answer is `npx ccusage` or any of the other of the trillion ways to see how many tokens you're getting”
Comment from 2 Sep 2026 in “Qwen3.8-Max” “You can use `npx ccusage` to check your local logs and see how much it would have cost through the API.”
Comment from 10 Mar 2026 in “No, it doesn't cost Anthropic $5k per Claude Code user” Useful for regular checks
“There’s also the ccusage package that I find useful.”
Comment from 23 Jan 2026 in “I was banned from Claude for scaffolding a Claude.md file” “I like to check in with ccusage pretty frequently”
Comment from 26 Aug 2026 in “GLM-5.3-Flash”
What people warn about
Each mark is one comment
Slow report generation
“The existing tool (ccusage) takes 17–20s to show a usage report”
Comment from 5 Mar 2026 in “Show HN: Tokenusage – Rust CLI that tracks Claude Code/Codex tokens 214x faster” “re-parses from scratch every time with no caching”
Comment from 5 Mar 2026 in “Show HN: Tokenusage – Rust CLI that tracks Claude Code/Codex tokens 214x faster”
Other usage trackers people recommend
The two most recommended other usage trackers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| ccusageThis page | 10 | 1 | 91% | 6 | — | Approved |
| agentsview | 9 | 1 | 90% | 5 | — | — |
| Claude Meter | 5 | 0 | 100% | 3 | — | — |
What people said
9 of the 12 comments that mention it, newest first. Each links to the original comment.
“the answer is `npx ccusage` or any of the other of the trillion ways to see how many tokens you're getting”
“I like to check in with ccusage pretty frequently”
“I second ccusage, it's nice”
“You can use `npx ccusage` to check your local logs and see how much it would have cost through the API.”
“re-parses from scratch every time with no caching”
“The existing tool (ccusage) takes 17–20s to show a usage report”
“want to see exactly what the damage will be if/when Anthropic decides to pull the rug”
“great libraries already exist for usage tracking (like ccusage)”
“There’s also the ccusage package that I find useful.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.