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.
