This is a known issue – Opus 4.7 in Max mode should show 1M context, and the 200K display is incorrect. Our team is actively investigating and working on a fix.
We’ll get this sorted. Let me know if you have any other questions!
The incorrect context window display for Opus 4.7 in Max mode has been addressed! The context ring should now correctly show 1M. Let me know if you are still running into this!
Hello, I am still experiencing this issue, however it is showing the 300k, instead of 200k. Also the bug isn’t just visual, as when the model hits 300k, it summarises the context, instead of using the remaining 700k heap.
Also, it seems that using the non-max with 1m token window is impossible, since the toggle also turns the max back on, if i try to select the 1m context, while clicking the “edit” in model selector.
@Colin I’m facing the same issue that @prosto_sanja is facing. Now it shows 300K as the context window and the chat context gets summarized every time it hits the 300k limit and isn’t just a visual bug.
Thanks for confirming, @shreyasa. @prosto_sanja — thanks for the details and screenshot as well.
Could one of you share a Request ID from an affected chat? You can find it via the three-dot menu in chat > Copy Request ID. That will help us trace what’s happening on the backend.
@prosto_sanja — regarding the model selector: 1M context does require Max mode, so that toggle behavior is expected.
When picking a 1M Model / Version the Context doesnt get updated to 1M it stays with the normal context limit of the Base Model.
Only Opus 4.6 seems to work, Opus 4.7 and GPT 5.5 dont work.
when changing the model while the context is already above the base models limit it will be set to the maximum context of the model = 100% context is being used. Chat summarization happens after that…
Steps to Reproduce
Create a new chat, choose Opus 4.7 or GPT 5.5 and select the 1M option. Send a message and hover over the context bar. It shows 272k / 300k Tokens as the limit tho it should have 1M or 929k or smth in that range. Change the model while in a current chat also shrinks the max context to the 272 / 300k limit…
Expected Behavior
When picking the 1M model it should get that context limit.
With Max Mode enabled and “1M Max” explicitly selected in the model picker, the context window indicator in the Agent panel consistently shows a 300K token maximum (e.g. ~23.6K / 300K Tokens) instead of the expected 1M tokens.
This affects all models that advertise 1M context support — not just Claude Opus 4.6 but also Claude 4.5 Sonnet and others. The 300K cap appears to be a hard UI/backend limit regardless of which 1M-capable model is selected.
Per Cursor’s own documentation and pricing page, Max Mode should extend the context window to the model’s full maximum (1M for Opus 4.6 and Sonnet 4.5), with no long-context surcharge. The 1M context window for these models went GA in March 2026.
Steps to Reproduce
Open Cursor IDE (v3.4.1 Nightly)
Open the Agent panel
Select any 1M-capable model (e.g. Opus 4.6)
Enable Max Mode (toggle “1M Max” in model selector)
Observe the context indicator — it shows X / 300K Tokens instead of X / 1M Tokens
Repeat with other 1M models (Sonnet 4.5, etc.) — same 300K cap
Expected Behavior
The context indicator should show X / 1M Tokens (or ~1,000K) when Max Mode is enabled on a model that supports a 1M context window. The full 1M context should be usable before any summarization or condensation kicks in.
The pattern suggests Cursor has an internal cap (possibly 300K or lower) that overrides the model’s actual context window, even when Max Mode is toggled on and the UI shows “1M Max” in the model selector.
Update: This started happening again today. Yesterday was completely fine, full 1M context working as expected. Same setup, same model, same “1M Max” toggle, now back to ~300K.
Honestly, what is Max Mode even for if the full context window isn’t guaranteed? Paying a premium for a feature that silently breaks overnight with no warning is not okay. You only notice when the agent starts losing context mid session because it condensed everything away.
Any update on what’s causing these regressions? @Colin@mohitjain
Opus 4.7 1M Max — context window capped at 300K on Ultra (regression)
Symptom: Opus 4.7 1M Max shows ~XXK / 300K Tokens in the Context panel
instead of the expected 1M denominator. Reproduces on every chat (new and existing),
across full Cursor restarts, with Max Mode toggled off->on, etc.
Worked correctly: A few days ago. Broken since: ~May 9–12, 2026 (correlates with build 3.3.30).
Environment:
Cursor: 3.3.30, build date 2026-05-09T18:28:42Z, commit 3dc5592
Plan: Ultra ($200/mo), on-demand at $1329.57 / $2000
Model: claude-opus-4-7-thinking-max (“Opus 4.7 ⊕ 1M Max” in selector)
Max Mode: ON (verified in model selector)
OS: Windows 10.0.26200
Request ID:
What I’ve ruled out:
Max Mode toggle is on (screenshot attached).
Model slug is the 1M Max variant (screenshot attached).
Plan supports it (Ultra includes Max; on-demand has $670 remaining).
Full Cursor restart doesn’t clear it.
Fresh chats also show 300K denominator.
No relevant settings.json customization.
Reference — adjacent Opus 4.7 1M regressions in the same week:
anthropics/claude-code#55504 (Opus 4.7 [1m] capped at 200K)
anthropics/claude-code#54056 (auto-compact at ~367K)
anthropics/claude-code#53199 (auto-compact far below 1M)
Different products, but the timing and shape of the regression suggest a
shared upstream issue with Opus 4.7’s 1M handling.
Same here. I saw opus 4.7 1M MAX the first time I enabled max mode (matching the GPT-5.5 1M median UI), but after a quick toggle, it only displays opus 4.7 MAX. I still haven’t been able to get the 1M context for Opus 4.7 to work consistently.
Same issue is happening with me, yesterday it was working well but today any model I choose with 1M it defaults back to 272K tokens and starts chat summarizing. Please help
So it’s not just me. Multiple people reporting the same regression today, all saying yesterday was fine. Looks like something broke on the backend overnight. @Colin@mohitjain@Condor@Sanjeed5 can we get some eyes on this?
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?
