claude-code - 💡(How to fix) Fix [BUG] Premium Team plan - degraded from 1M to 200k token since outage on Apr 13, 2026 [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#47896Fetched 2026-04-15 06:39:14
View on GitHub
Comments
1
Participants
2
Timeline
6
Reactions
0
Author
Timeline (top)
labeled ×5commented ×1
RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues and this hasn't been reported yet
  • This is a single bug report (please file separate reports for different bugs)
  • I am using the latest version of Claude Code

What's Wrong?

After the outage on Apr 13, 2026 I had to re-login my Claude Code instance to my premium team account, which was working fine with 1M token window before, even on the same day. After having logged in again my context window is back to 200k.

I even updated to the latest Claude Code version, but that did not do the trick.

What Should Happen?

1M token context after login

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

2.1.96, did upgrade trying to solve the problem afterwards

Claude Code Version

2.1.107

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

iTerm2

Additional Information

No response

extent analysis

TL;DR

The issue may be resolved by downgrading to version 2.1.96, as the 1M token context window was working in that version.

Guidance

  • Verify that the issue persists after re-logging in to the premium team account with the latest version (2.1.107) to confirm the regression.
  • Check the release notes or changelog for versions 2.1.97 to 2.1.107 to see if any changes were made that could have caused the token context window to revert to 200k.
  • Test the Opus model with a smaller token window to see if the issue is specific to the 1M token context.
  • Consider reaching out to the development team or support for further assistance, as the issue may be related to the Anthropic API or a specific configuration.

Notes

The issue seems to be specific to the Opus model and the 1M token context window, and downgrading to version 2.1.96 may not be a permanent solution. Further investigation is needed to determine the root cause of the regression.

Recommendation

Apply workaround: Downgrade to version 2.1.96, as it is the last known working version for the 1M token context window. This is a temporary solution until the root cause of the regression can be determined and fixed.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING