Claude Code usage tracking by LangWatch is a specialized developer tool designed to give you complete visibility into what your Claude Code sessions actually cost. Built for AI engineers and developers leveraging terminal-based AI coding workflows, this tool provides granular insights into token usage, caching efficiency, and session executions.

Getting started is frictionless—you simply need to run npx langwatch claude once. From there, the tool automatically tracks every session, breaking down costs with cache reads and writes as separate token classes. It logs every bash and Model Context Protocol (MCP) call as an individual span, compares theoretical usage versus billed usage for your Max plan, and delivers a full terminal replay directly in the user interface. Additionally, it offers support for Codex.

Pros of Claude Code usage tracking by LangWatch

Extremely easy setup with a single command (`npx langwatch claude`)
Detailed cost breakdown including cache reads and writes as separate token classes
Tracks every bash and MCP call as individual spans
Provides a full terminal replay in the UI and supports Codex as well

Cons of Claude Code usage tracking by LangWatch

Requires integration with LangWatch for tracking and UI visualization
Focused primarily on terminal-based coding assistant workflows like Claude Code and Codex

Frequently Asked Questions

How do I start tracking my Claude Code sessions?

You can start tracking your sessions instantly by running the command `npx langwatch claude` once.

What metrics and data points does LangWatch capture?

It tracks session costs, cache reads and writes as separate token classes, theoretical vs billed usage for your Max plan, individual spans for bash and MCP calls, and provides a full terminal replay in the UI.