`stream disconnected before completion` on `RPM`

Resolved 💬 9 comments Opened Jan 28, 2026 by guidedways Closed Jan 28, 2026

💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

v0.92.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.2-xhigh

What platform is your computer?

macOS

What terminal emulator and version are you using (if applicable)?

iTerm

What issue are you seeing?

• Reconnecting... 1/5 (5s • esc to interrupt)
  └ Stream disconnected before completion: Rate limit reached for organization org-BOvpEHVcDPTe8h4lZnwMO5Ly on input-images per min: Limit 10, Used 10, Requested 2. Please try again
    in 12s. Visit https://platform.openai.com/account/rate-limits to learn more.

What steps can reproduce the bug?

Uploaded thread: 019bffdc-c6fb-7802-8ef3-0be58033c369

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

9 Comments

github-actions[bot] contributor · 5 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

#10058
#10057
#10056
#10055
#10051

Powered by Codex Action

guidedways contributor · 5 months ago

Trying this with a second account, same issue:

• Reconnecting... 1/5 (20s • esc to interrupt)
  └ Stream disconnected before completion: Rate limit reached for organization org-ABC on tokens per min (TPM): Limit 250000, Used 250000, Requested 89623.
    Please try again in 21.509s. Visit https://platform.openai.com/account/rate-limits to learn more.

JKamsker · 5 months ago

Same

ssh352 · 5 months ago

same

theblackboxinyourhead · 5 months ago

seems only the vanilla gpt-5.2 models are down, the codex variants work

JKamsker · 5 months ago

Wakey wakey @etraut-openai

var-gg · 5 months ago

same

ahmedelami · 5 months ago

This worked for me:

The issue was a stale, cached authentication session in the local config (it was prioritizing an old/limited API Org that i have no idea where it came from nor what prompted it...? instead of my ChatGPT subscription).

Kill lingering processes and remove the cached auth file:

pkill -f codex
rm ~/.codex/auth.json

Start fresh (forcing no env vars to ensure a clean login):

env -u OPENAI_API_KEY -u OPENAI_ORGANIZATION codex

Then just resign in with "Sign in with ChatGPT" when prompted.

etraut-openai contributor · 5 months ago

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.