1M context models missing after Max Mode removal

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

After the removal of Max Mode, the 1M-context models no longer appear in the model picker.

In your July 13 email titled “Removing Max Mode on July 20th,” you stated that the same context window sizes would remain available and could be selected directly from the model picker. However, I can currently only see the 300K versions (screenshot attached).

Is this a bug, or has the 1M context option been moved elsewhere?

Steps to Reproduce

Go to Settings → Models and try to find a 1M model listed.

Expected Behavior

To see both 300k models and 1M models to choose from.

Screenshots / Screen Recordings

Operating System

Windows 10/11

Version Information

Version: 3.13.25 (user setup)
VS Code Extension API: 1.128.0
Commit: 31e8d61c448c7472e371505838a0fe34083dad50
Date: 2026-07-28T06:17:45.069Z
Layout: Agent Window
Build Type: Stable
Release Track: Default
Electron: 40.10.3
Chromium: 144.0.7559.236
Node.js: 24.15.0
V8: 14.4.258.32-electron.0
xterm.js: 6.1.0-beta.256
OS: Windows_NT x64 10.0.22631

Does this stop you from using Cursor

No - Cursor works, but with this issue

Hi @Bit Thanks for the forum post!

Max Mode was recently removed for most individual plans, see more info here: What does Cursor removing “Max Mode” mean for usage-based pricing users? So that part is real. The 1M context windows it used to unlock are still there. Settings > Models used to list each parameter combination as its own entry, which is where you’d have seen the 1M versions. Those are now grouped into one row per model family, so you get a single Opus 5 or GPT-5.6 Sol entry instead of one row per size, with the parameters themselves moved into the chat model picker. The “272k context window” tooltip is that model’s default, not a cap.

To pick 1M, open the model picker in a chat, hover the model’s row, click Edit, then set Context to 1M. You’ll find Fast and Thinking in the same place, and the choice sticks for that model. Lmk if you have any follow-up questions!