Pro and Max subscribers get a progress bar. This gives you the full picture.
Claude Code writes detailed usage logs locally — token counts, models, sessions, projects — regardless of your plan. This dashboard reads those logs and turns them into charts and cost estimates. Works on API, Pro, and Max plans.
Created with Claude Code by Ivan Pogosov
Forked from phuryn/claude-usage
Works on API, Pro, and Max plans — Claude Code writes local usage logs regardless of subscription type. This tool reads those logs and gives you visibility that Anthropic's UI doesn't provide.
Captures usage from:
- Claude Code CLI (
claudecommand in terminal) - VS Code extension (Claude Code sidebar)
- Dispatched Code sessions (sessions routed through Claude Code)
Not captured:
- Cowork sessions — these run server-side and do not write local JSONL transcripts
- Python 3.8+
- No third-party packages — uses only the standard library (
sqlite3,http.server,json,pathlib)
Anyone running Claude Code already has Python installed.
No pip install, no virtual environment, no build step.
git clone https://github.com/ipogosov/claude-usage
cd claude-usage
python cli.py dashboard
git clone https://github.com/ipogosov/claude-usage
cd claude-usage
python3 cli.py dashboard
On macOS/Linux, use
python3instead ofpythonin all commands below.
# Scan JSONL files and populate the database (~/.claude/usage.db)
python cli.py scan
# Show today's usage summary by model (in terminal)
python cli.py today
# Show all-time statistics (in terminal)
python cli.py stats
# Scan + open browser dashboard at http://localhost:8087
python cli.py dashboard
The scanner is incremental — it tracks each file's path and modification time, so re-running scan is fast and only processes new or changed files.
Claude Code writes one JSONL file per session to ~/.claude/projects/. Each line is a JSON record; assistant-type records contain:
message.usage.input_tokens— raw prompt tokensmessage.usage.output_tokens— generated tokensmessage.usage.cache_creation_input_tokens— tokens written to prompt cachemessage.usage.cache_read_input_tokens— tokens served from prompt cachemessage.model— the model used (e.g.claude-sonnet-4-6)
scanner.py parses those files and stores the data in a SQLite database at ~/.claude/usage.db.
dashboard.py serves a single-page dashboard on localhost:8087 with Chart.js charts (loaded from CDN). It auto-refreshes every 30 seconds and supports model filtering with bookmarkable URLs.
Costs are calculated using Anthropic API pricing as of April 2026 (claude.com/pricing#api).
Only models whose name contains opus, sonnet, or haiku are included in cost calculations. Local models, unknown models, and any other model names are excluded (shown as n/a).
| Model | Input | Output | Cache Write | Cache Read |
|---|---|---|---|---|
| claude-opus-4-6 | $6.15/MTok | $30.75/MTok | $7.69/MTok | $0.61/MTok |
| claude-sonnet-4-6 | $3.69/MTok | $18.45/MTok | $4.61/MTok | $0.37/MTok |
| claude-haiku-4-5 | $1.23/MTok | $6.15/MTok | $1.54/MTok | $0.12/MTok |
Note: These are API prices. If you use Claude Code via a Max or Pro subscription, your actual cost structure is different (subscription-based, not per-token).
| File | Purpose |
|---|---|
scanner.py |
Parses JSONL transcripts, writes to ~/.claude/usage.db |
dashboard.py |
HTTP server + single-page HTML/JS dashboard |
cli.py |
scan, today, stats, dashboard commands |