Rate limit reached for organization on tokens per min (TPM)
What version of Codex is running?
0.92
What subscription do you have?
Pro
Which model were you using?
gpt-5.2
What platform is your computer?
windows wsl
What terminal emulator and version are you using (if applicable)?
codex cli
What issue are you seeing?
I checked the documentation for this limit, which should be the limit of the API? I am a Pro subscriber and using the official client of codex cli (in wsl environment), I tried to open a new thread and enter hello and I also get this error
• Reconnecting... 3/5 (10s • esc to interrupt)
└ Stream disconnected before completion: Rate limit reached for organization org-BOvpEHVcDPTe8h4lZnwMO5Ly on tokens per min (TPM): Limit 250000, Used 250000, Requested 18667. Please try again in 4.48s. Visit https://platform.openai.com/account/rate-limits to learn more
Meanwhile, I checked my usage/status
5h limit: [███████████████████░] 97% left (resets 13:33)
│ Weekly limit: [████████████████░░░░] 78% left (reloaded 23:13 on 31 Jan)
I tried to start codex in another small warehouse and type hello, and it gave the same prompt, but it showed 3000 Uesd 3000 limit
What steps can reproduce the bug?
Uploaded thread: 019c027a-d0cf-7750-ad4b-21b0c60d6abc
What is the expected behavior?
_No response_
Additional information
I updated to 0.92 before this issue, and added
~/.codex/config.toml
collab = true
collaboration_modes = true
Then I did a small bug fix, but I deleted the configuration after the problem occurred, but I couldn't go back to normal
7 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
same
<img width="2017" height="68" alt="Image" src="https://github.com/user-attachments/assets/fbc56953-a29b-4bc6-80b9-ddb9144bf870" /> same, not the same org as in my setting, on starlink
It looks like all requests are counted under the same organization, causing concurrency limits. I'm also having issues with org-BOvpEHVcDPTe8h4lZnwMO5Ly, which is an issue with the organization's TPM limit
This worked for me:
The issue was a stale, cached authentication session in the local config (it was prioritizing an old/limited API Org instead of my ChatGPT subscription).
Lmk if it also works for you or helps?
It seems that the official has fixed the bug and it is now working as normal
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.