---
title: "Claude Code Usage Analyzer"
description: "Analyze your Claude Code usage locally. Drop your JSONL session files and get instant charts for token usage, costs, model breakdown, and cache analysis. 100% private, nothing leaves your browser."
url: https://findutils.com/developers/claude-code-usage-analyzer/
category: developers
---

# Claude Code Usage Analyzer

Analyze your Claude Code usage locally. Drop your JSONL session files and get instant charts for token usage, costs, model breakdown, and cache analysis. 100% private, nothing leaves your browser.

**Use this tool:** [Claude Code Usage Analyzer](https://findutils.com/developers/claude-code-usage-analyzer/)

## Programmatic access

- Browser-only: this tool works on a file, the DOM, or a browser API and has no REST or MCP id.

## Why Use Claude Code Usage Analyzer?

Claude Code subscriptions show a progress bar with your usage percentage, but no breakdown by model, project, or day. This tool reads the JSONL session files that Claude Code already writes to your machine at ~/.claude/projects/ and turns them into a visual dashboard. Every session, every turn, every token is logged locally: input tokens, output tokens, cache reads, cache creation, model name, and timestamp. This analyzer processes those files entirely in your browser to give you cost estimates, usage trends, and cache analysis without sending a single byte to any server. Whether you want to understand which model costs the most, track your daily usage patterns, or investigate cache token spikes, this dashboard gives you the visibility that the Claude Code UI does not provide.

## Frequently Asked Questions

### Where are Claude Code session files stored?

Claude Code writes JSONL session files to ~/.claude/projects/ on your machine. Each project gets its own subdirectory with conversation logs containing token counts, model info, and timestamps.

### Is my data sent to any server?

No. All processing happens entirely in your browser using JavaScript. Your session files are read locally and never uploaded anywhere. You can verify this in your browser's network tab.

### How are costs calculated?

Costs are taken directly from the costUSD field in each JSONL entry, which Claude Code records per-turn. These represent API-equivalent costs based on Anthropic's pricing at the time of the session.

### Can I analyze multiple projects at once?

Yes. You can drop an entire folder or select multiple.jsonl files. The analyzer will process all files and aggregate the data across projects, sessions, and models.

### What do cache tokens mean?

Cache read tokens are tokens served from Anthropic's prompt cache instead of being reprocessed. Cache creation tokens are tokens written to the cache for future reuse. High cache read ratios indicate efficient context reuse across conversation turns.

### Does the analyzer require a signup?

No. It is available with no signup and no usage limits. Session files are parsed in your browser and never uploaded.

### Can I export the analysis?

Yes. The dashboard has Export JSON and Export CSV buttons that write the computed usage data out for a spreadsheet or a report, so you can keep a record without keeping the raw session files.

### Which charts does the dashboard show?

Token usage over time, cost, a breakdown by model, and cache analysis for the sessions you drop in. Each chart reads the same parsed data, so the totals agree with each other.

## Related Tools

- [JSON Formatter](https://findutils.com/developers/json-formatter/)
- [JSON Visualizer](https://findutils.com/developers/json-visualizer/)
- [AI Model Picker](https://findutils.com/developers/ai-model-picker/)
- [JWT Decoder](https://findutils.com/developers/jwt-decoder/)