I selected the Opus 4.7 1M model, but the actual context limit is 300K

Support Bug Reports
, ,
1

Describe the Bug

Hello, when using Cursor, I selected the Opus 4.7 1M model. However, during my conversation, I noticed that the limit seems to be 300K tokens. Once it reaches 300K, my conversation is automatically compressed. What is the reason for this?

Steps to Reproduce

Hello, when using Cursor, I selected the Opus 4.7 1M model. However, during my conversation, I noticed that the limit seems to be 300K tokens. Once it reaches 300K, my conversation is automatically compressed. What is the reason for this?

Screenshots / Screen Recordings

666.png
666.png1626×732 54.3 KB

Operating System

MacOS

Version Information

Version: 3.3.30
VSCode Version: 1.105.1
Commit: 3dc559280adc5f931ade8e25c7b85393842acf30
Date: 2026-05-09T18:28:42.332Z
Layout: glass
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Darwin arm64 25.3.0

For AI issues: add Request ID with privacy disabled

request id 8c82bfdb-e28d-4e6f-915f-8f0e3566a820

Does this stop you from using Cursor

Yes - Cursor is unusable

5

Hey, yeah, this is a known issue. With Max mode enabled on Opus 4.7, the real context cap is about 300K and auto-summarization kicks in, even though the UI shows 1M. It’s a bug on our side, the team is aware, but I can’t share an ETA yet.

We’re tracking it here: Opus 4.7 Max mode shows only 200K context instead of 1M. You can subscribe there so you don’t miss the fix update.