What is ccusage?
ccusage is a CLI tool that analyzes Claude Code token usage and costs from local JSONL files. Track your daily, monthly, and session-based usage with beautiful tables and comprehensive reporting.Key features
Daily and monthly reports
View token usage and costs aggregated by date or month with beautiful table formatting
Session tracking
Analyze usage grouped by conversation sessions to understand project-level costs
5-hour billing blocks
Track usage within Claude’s billing windows with active block monitoring
Model breakdown
See which Claude models you’re using (Opus, Sonnet) with per-model cost analysis
Cache token support
Tracks cache creation and cache read tokens separately for accurate cost tracking
JSON output
Export data in structured JSON format for programmatic consumption and automation
Project analysis
Group usage by project with
--instances flag and filter by specific projectsMCP integration
Built-in Model Context Protocol server for integration with Claude Desktop and other tools
Why ccusage?
- Ultra-small bundle size - Incredibly lightweight even without minification, perfect for instant execution with
npx - Offline mode - Use pre-cached pricing data without network connectivity (Claude models only)
- Smart tables - Automatic compact mode for narrow terminals with essential columns
- Timezone support - Configure timezone for date grouping with
--timezoneoption - Locale support - Customize date/time formatting with
--localeoption (e.g., en-US, ja-JP, de-DE) - Configuration files - Set defaults with JSON configuration files, complete with IDE autocomplete and validation
ccusage family
ccusage is part of a family of usage analysis tools:- ccusage - Claude Code usage analyzer
- @ccusage/codex - OpenAI Codex usage analyzer
- @ccusage/opencode - OpenCode usage analyzer
- @ccusage/pi - Pi-agent usage analyzer
- @ccusage/amp - Amp usage analyzer
- @ccusage/mcp - MCP server integration
Next steps
Installation
Install ccusage with your preferred package manager
Quick start
Get started with your first usage report