Claude Code usage tracking by LangWatch - See what your Claude Code sessions actually cost
by•
Track Claude Code usage: cost, cache, session replay. Run `npx langwatch claude` once. Every session gets cost with cache reads/writes as separate token classes, every bash and MCP call as a span, theoretical vs billed for your Max plan, and a full terminal replay in the UI. Works for Codex too.
Replies
Documentation.AI
The combination of cost tracking, session replay, and tool tracing makes this much more than another analytics dashboard. Congrats on launching!!!
LangWatch
@roopreddy that's right! LangWatch is currently the most powerfull observability tool for it! But I might be a bit bias! ;)
Pazi
Knowing exactly what each Claude Code session costs is a game changer. Congrats on the launch, this is awesome! 🚀
LangWatch
@zvonimir_sabljic1 thanks, this is just the beginning!
LangWatch
@zvonimir_sabljic1 thanks 🙏 let us know once you’ve tried
LangWatch
This is such a killer feature for heavy users and big teams with distributed sessions leveraging multiple providers! Great work, @LangWatch !
great product! knowing the per-seat cost but not which sessions burned is a proper problem, especially as the costs keep rising. this is going to save me from getting broke!
LangWatch
@lina_dikhtiaruk hope ai coding solutions will also bring your team / product / company the speed and competitie advantage to win the game and get more revenue in ,! But we’ll def be there to nbe more efficient
really proud of this launch!
LangWatch
@aryan_sharma78 100%
the MCP tool calls as spans is the bit i want most. i drive a browser automation MCP from claude code all day and the screenshots are obviously the expensive part, except obviously is doing a lot of work in that sentence because i have no per-call number for any of it.
cache reads and writes counted separately is the other one, that is where the surprise usually hides.
LangWatch
@alex_watson2110 yeeppp both are in there: every MCP call gets its own span with its own token cost, and cache reads and writes are broken out separately, so you'll have a real per-screenshot number instead of a hunch.
Lancepilot
LangWatch
@priyankamandal interesting use-case!
Lancepilot
Can the platform can identify inefficient prompting patterns across multiple sessions?
LangWatch
@imtiaj_ahmad That's exactly where we're headed, this is the groundwork for it, so what kinds of suggestions would actually be useful to you?
BetterClaw
Congrats on shipping this! Finally a way to know exactly how much those late-night Claude Code sessions are costing me. My wallet thanks you already!
LangWatch
@better_shaya haha very welcome!