[BUG] All 1M context models rate limited on first message, Pro plan

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?

Both Sonnet 4.6 1M and Opus 4.6 1M are rate limited on the first API call of a new session, with zero context accumulated.

Plan: Pro
Models tested: Sonnet 4.6 (1M context), Opus 4.6 (1M context)
Status: Rate limited immediately on first message, every session

Tried:

• Complete session restart
• Fresh session with no prior context
• Different models (both 1M variants fail)

Standard context models (without 1M) work fine. Issue appears specific to extended context tier.

What Should Happen?

Sonnet 4.6 1M and Opus 4.6 1M should work normally on Pro plan without rate limit on the first message of a new session, like all other available models.

Error Messages/Logs

Steps to Reproduce

1. Use Claude Code on Pro plan
2. Open a new fresh session (no prior context)
3. Switch to Sonnet 4.6 1M or Opus 4.6 1M model
4. Send any first message
5. Observe: "Rate limit reached" error appears immediately

Claude Model

Not sure / Multiple models

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

v2.1.84

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_