Your pinned model switched unexpectedly after an update
Responses feel faster but less thorough than they used to be
You need deep reasoning on a hard problem and aren't sure how to enable it
You're on Max or Team and noticed different behavior without changing any settings
Changes in Claude Code v2.1.68
Removed1 change
•Removed Opus 4 and 4.1 from Claude Code on the first-party API — users with these models pinned are automatically moved to Opus 4.6
Other2 changes
•Opus 4.6 now defaults to medium effort for Max and Team subscribers. Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness. You can change this anytime with /model
•Re-introduced the "ultrathink" keyword to enable high effort for the next turn