Track your OpenCode usage | LangWatch
Track your OpenCode Usage
Or Claude Code, Codex, Copilot, Cursor, and Pi. Capture full trace history to improve your flow, and track how much you're spending in tokens.
Start tracking right away:
npx langwatch opencode
Trace Summary
| Origin | Duration | Cost | Tokens | Spans | Model |
|---|---|---|---|---|---|
| Coding Agent | 2307.1s | $221.02 | 488.8K | 557 | gpt-5.6-sol |
Input and Output Examples
Input: I did the gcloud auth login hopefully you can continue?
Output: The scan came back empty: no project in your account has the Google Ads API enabled at all, which actually pins the diagnosis. Modern Ads API accounts declare their Cloud project explicitly in th…
Input: I have several design change requests here [Image #7]
Output: All three are in: clawd is a die-cut sticker on the right with the slow wobble, the trace colors match the app tokens, and the span tree groups repeats with ×N pills…
Input: ok merged! but /reuse-worktree cuz already found a bug
Output: Worktree reset to latest main on a fresh branch. The bug reproduces: the retry queue drops the last event when the worker restarts. Writing the failing test first, fix goes on the same PR…
Analyzing Token Usage
Theoretical vs Billed Costs
| Model | Theoretical Cost | Billed Cost |
|---|---|---|
| gpt-5.6-sol | $20,795 | $200 |
| kimi-k2.5 | $0.00 | $3,695 |
| claude-fable-5 | $200.00 | $200 |
FAQ
How do I track my OpenCode usage?
Run npx langwatch opencode. It configures OpenCode’s OpenTelemetry export to LangWatch, whichever provider your models run on.
Does it work with Claude Code, Codex, Copilot, Cursor, and Pi?
Yes. Each agent exports through the same OTLP endpoint.
What does the "Bundled" cost label mean?
Sessions on a provider subscription you signed into have no per-token invoice. LangWatch marks those sessions Bundled.
Insights to Improve Your Skills
Run Claude over your own trace history: what you asked for, what helped most, and the friction patterns where sessions go wrong.