Explore leaderboards with expert-driven LLM benchmarks and updated AI model rankings across coding, reasoning and more.
ccusage
ccusage analyzes token usage and estimated costs for coding agent command-line tools.
About ccusage
ccusage is a command-line tool that reads local usage logs from coding agent CLIs and reports token counts and estimated costs in USD. By default it shows usage from all detected supported tools, and users can narrow the same views to one source. Output appears in terminal tables that adjust to wide and narrow windows, and results can be exported as JSON.
Costs are estimates calculated from token counts and model pricing, with cache token accounting applied where available. Claude Code blocks and statusline views are limited to Claude Code because they depend on Claude-specific local data and hooks.
Key features
- Tracks tokens and estimated costs across 18 supported coding agent CLIs
- Reads local usage logs and states that it does not upload your data
- Estimates USD spend from token counts and model pricing
- Tracks cache creation and cache read tokens separately
- Exports usage data in structured JSON format
- Offline mode uses pre-cached pricing data without network connectivity
Best for: Developers who use several coding agent command-line tools and want token usage and estimated spend shown in one place.
Good for
- Shows usage from many supported coding agent CLIs in one view, with the option to filter to a single source
- Reads local usage logs, and the homepage states that data is not uploaded
- Can run offline using pre-cached pricing data
Watch out for
- Costs are estimates based on token counts and model pricing, not billing records
- Claude Code blocks and statusline depend on Claude-specific local data and hooks
- Cache-related cost accounting applies only where it is available
ccusage at a glance
- Website
- ccusage.com
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
ccusage alternatives
Tools and sites you could use instead, ranked by how closely they match.
Calculate language model API costs using input, cached input, and output token counts.
DeepSWE benchmarks coding agents on long-horizon software engineering tasks and publishes a leaderboard.
Fiddler provides evaluation, monitoring, enforcement, governance, and cost controls for enterprise AI agents.
OpenRouter publishes language model rankings based on real usage through its API.
PricePerToken compares API costs for language models from multiple providers.
Popular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
ccusage FAQ
Does ccusage upload my usage data?
The homepage states that ccusage reads local usage logs from supported tools without uploading your data.
Can I use ccusage without a network connection?
Offline mode uses pre-cached pricing data without network connectivity.
Which coding agent tools does ccusage support?
The homepage lists Claude Code, Codex, OpenCode, Amp, Droid, Codebuff, Hermes Agent, pi-agent, Goose, OpenClaw, Kilo, Kimi, Qwen, GitHub Copilot CLI, Gemini CLI, Antigravity, Grok Build CLI, and ZCode.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.