[BUG] Session usage metrics inconsistent between Claude Code app and web
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
Multiple sessions display different token counts when viewed in the Claude Code app versus on the web at claude.ai. The discrepancies are significant and affect usage limit tracking and cost calculation. Token counts (input, output, cache read, cache write) do not match between the two surfaces for the same session.
What Should Happen?
Token counts should be identical across surfaces (app and web) for the same session.
Error Messages/Logs
Steps to Reproduce
- Run a session in Claude Code app
- Check usage on the web at claude.ai
- Check the same session's usage in the Claude Code app
- Compare the token counts
Examples of discrepancies:
Fable 5 session:
Web: 85.8k input, 121.2k output, 44.8M total
App: 56.4k input, 250.1k output, 31.5M total
Opus 4.8 session:
Web: 31.0k input, 536.2k output, 68.0M total
App: 55.3k input, 11.2k output, 93.9M total
Claude Model
Not sure / Multiple models
Is this a regression?
I don't know
Last Working Version
_No response_
Claude Code Version
Claude 1.11847.5 (9692f0) 2026-06-09T17:34:27.000Z
Platform
Anthropic API
Operating System
Windows
Terminal/Shell
Terminal.app (macOS)
Additional Information
Ssession 1
App
<img width="534" height="235" alt="Image" src="https://github.com/user-attachments/assets/9c6accfe-ad02-4066-bb63-6124523f67c9" />
Web
<img width="538" height="235" alt="Image" src="https://github.com/user-attachments/assets/f6bfa811-5390-46f2-b57a-9cb0c86e2890" />
Session 2
App
<img width="539" height="238" alt="Image" src="https://github.com/user-attachments/assets/bd43a9d7-e80a-48c0-bff3-73faadc53734" />
Web
<img width="543" height="249" alt="Image" src="https://github.com/user-attachments/assets/7e93e1d6-0bbb-4f4c-b330-4ff65e05760e" />