Stream disconnected before completion: Rate limit reached for organization
Resolved 💬 5 comments Opened Jan 28, 2026 by uimodel Closed Jan 28, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
I am a GPT Pro user, and I am currently experiencing rate limits. Similar issues have occasionally occurred in the past few months. I am still within my subscription period, but I am unable to use it anymore.
5 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
thread ID 019c02bc-8c23-74b3-9c41-633e9103da56
It has been confirmed that only the GPT 5.2 model cannot be used, while the GPT Codex can be used normally. Is this strange? There is still a lot of quota left.
I just had the same very bad surprise. I never got that issue before and actually I have been using it more moderately this week. Message:
<img width="764" height="119" alt="Image" src="https://github.com/user-attachments/assets/e2bf64a1-3ffb-44b9-b75f-02e9ec8fdefa" />
And the message is wrong as i litteraly just woke up and this was my first query. This seems to be a new limit. It would be nice if openai could confirm what's happening. And yes, i only use GPT5.2 xhigh and no, I am not interested in using 5.2 codex.
Thanks for reporting. There was a temporary service issue that caused the responses API to incorrectly report rate limit errors when it shouldn't. The issue has been mitigated. Everything should be back to normal now. Apologies for the disruption.