[BUG] Inconsistent "extra usage" selections between Opus, Sonnet, 200K, and 1M contexts

Resolved 💬 4 comments Opened Apr 20, 2026 by GeoffNordling Closed Jun 11, 2026

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?

The /model picker labels Claude Sonnet 4.6 (1M context) as "Billed as extra usage," but this appears to be a bug.

Observations:

  • Opus 4.7 1M is the only Opus option available — no non-1M variant exists — and it does not carry the "extra usage" label
  • Sonnet 4.6 has both a standard and 1M variant; only the 1M is labeled as extra usage

What Should Happen?

Expected behavior:
If the 1M context Opus model is not billed as extra usage, the 1M context Sonnet model should be consistent, or the billing difference should be documented and explained.

Question:
Is the Sonnet 4.6 1M context window actually billed differently than Opus 4.7 1M, or is this label a UI bug?

Error Messages/Logs

OS:
Fedora

Claude Code version:
Version 2.1.114

Direct paste of /model selection screen from terminal:
Select model                                                                                                                            
  Switch between Claude models. Applies to this session and future Claude Code sessions. For other/previous model names, specify with       
  --model.                                                                                                                                  
                                                                                                                                            
    1. Default (recommended)  Opus 4.7 with 1M context · Most capable for complex work                                                  
    2. Sonnet                 Sonnet 4.6 · Best for everyday tasks                                                                          
  ❯ 3. Sonnet (1M context) ✔  Sonnet 4.6 with 1M context · Billed as extra usage · $3/$15 per Mtok                                          
    4. Haiku                  Haiku 4.5 · Fastest for quick answers

Steps to Reproduce

Type /model and see what happens.

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

2.1.114

Platform

Anthropic API

Operating System

Other Linux

Terminal/Shell

Other

Additional Information

_No response_

View original on GitHub ↗

This issue has 4 comments on GitHub. Read the full discussion on GitHub ↗