A comprehensive token usage and cost tracking tool for Claude Code and Codex CLI.
This tool combines usage data from both ccusage (Claude) and ccusage-codex (Codex) to provide a unified view of your AI token consumption and associated costs.
pip install ai-usage-tracker
ai-usage-trackernpm install -g ai-usage-tracker
ai-usage-tracker-jsgit clone https://github.com/jleechanorg/ai-usage-tracker.git
cd ai-usage-tracker
# Install dependencies (ccusage and ccusage-codex)
./scripts/install-dependencies.sh
# Run the report
python3 scripts/combined-usage-report.py
# Or install as a Claude skill
ln -s $(pwd)/.claude/skills/combined-usage ~/.claude/skills/combined-usage
# Then use: /combined-usage- Combined Reporting: View Claude and Codex usage side-by-side
- Cost Analysis: Track spending across both platforms
- Daily Averages: Calculate average usage over time
- Cache Efficiency: Monitor cache read rates and savings
- Flexible Output: Table format for humans, JSON for automation
- Claude Skill: Invoke directly from Claude Code CLI
pip install ai-usage-trackernpm install -g ai-usage-trackergit clone https://github.com/jleechanorg/ai-usage-tracker.git
cd ai-usage-tracker
pip install .Both the pip and npm packages require ccusage and ccusage-codex CLI tools:
npm install -g ccusage @ccusage/codexOr use the automated installation script:
./scripts/install-dependencies.shln -s $(pwd)/.claude/skills/combined-usage ~/.claude/skills/combined-usage# Default: Last 7 days
ai-usage-tracker
# Custom date range
ai-usage-tracker --days 14
# JSON output
ai-usage-tracker --json# Default: Last 7 days
ai-usage-tracker-js
# Custom date range
ai-usage-tracker-js --days 14
# JSON output
ai-usage-tracker-js --jsonpython3 scripts/combined-usage-report.py
python3 scripts/combined-usage-report.py --days 14
python3 scripts/combined-usage-report.py --jsonIf installed as a skill:
/combined-usage
╔════════════╦═══════════════╦════════════╦═══════════════╦════════════╦═══════════════╦════════════╗
║ Date ║ Claude Tokens ║ Claude $ ║ Codex Tokens ║ Codex $ ║ Total Tokens ║ Total $ ║
╠════════════╬═══════════════╬════════════╬═══════════════╬════════════╬═══════════════╬════════════╣
║ 02-11 ║ 88,155,247 ║ $ 37.31 ║ 67,371,956 ║ $ 12.82 ║ 155,527,203 ║ $ 50.13 ║
║ 02-10 ║ 368,293,666 ║ $ 160.69 ║ 764,117,407 ║ $ 144.86 ║ 1,132,411,073 ║ $ 305.55 ║
...
╚════════════╩═══════════════╩════════════╩═══════════════╩════════════╩═══════════════╩════════════╝
DAILY AVERAGES (Last 7 complete days)
Claude: 237,410,924 tokens/day | $123.39/day
Codex: 511,863,756 tokens/day | $98.76/day
TOTAL: 749,274,679 tokens/day | $222.15/day
See docs/usage-report.md for a complete example report with insights and recommendations.
| Package | Registry | Install |
|---|---|---|
| ai-usage-tracker | PyPI | pip install ai-usage-tracker |
| ai-usage-tracker | npm | npm install -g ai-usage-tracker |
ai-usage-tracker/
├── README.md # This file
├── CHANGELOG.md # Version history
├── pyproject.toml # Python package config (PyPI)
├── ai_usage_tracker/ # Python package source
│ ├── __init__.py
│ └── cli.py # CLI entry point
├── npm/ # Node.js package source
│ ├── package.json # npm package config
│ ├── tsconfig.json
│ └── src/
│ ├── index.ts # Library exports
│ ├── tracker.ts # Core logic
│ └── cli.ts # CLI entry point
├── docs/
│ └── usage-report.md # Example report with analysis
├── scripts/
│ ├── install-dependencies.sh # Automated installation script
│ └── combined-usage-report.py # Original report generator
└── .claude/
└── skills/
└── combined-usage # Claude skill definition
Based on typical usage patterns:
- Token Distribution: Codex typically accounts for ~67% of total tokens
- Cost Ratio: Claude tokens are ~2.8x more expensive than Codex tokens
- Cache Efficiency: Both tools maintain 90%+ cache read rates
- Average Daily Cost: Typically ranges from $150-250/day for heavy usage
Contributions welcome! Please feel free to submit issues or pull requests.
MIT License - Feel free to use and modify as needed.
Built for tracking usage across:
