›_ Codex Issues
Codex Issues / #334

Crashed with rate limit

Resolved 💬 10 comments Opened Apr 18, 2025 by ashish01 Closed Apr 22, 2025
💡 Likely answer: A maintainer (jonchurch, contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

v0.1.2504172351

Which model were you using?

gpt-4.1

What platform is your computer?

Darwin 23.2.0 arm64 arm

What steps can reproduce the bug?

Crashed with

e [Error]: Rate limit reached for gpt-4.1 in organization ... on tokens per min (TPM): Limit 30000, Used 25890, Requested 4193. Please try again in 166ms. Visit https://platform.openai.com/account/rate-limits to learn more.

What is the expected behavior?

please don't crash

What do you see instead?

_No response_

Additional information

_No response_

View original on GitHub ↗

10 Comments

calvinlacock · 1 year ago

Same - drives me insane - cant use it .. back to Claude until they work this out - cant keep paying for 1/2 baked code

ajstair · 1 year ago

Because Codex uses any regular OpenAI API key, rate limits that apply to keys in your org will also apply to Codex as it makes API requests. I'm assuming here, but it's very likely that your organization is subject to Tier 1 usage rate limits.

Here are a few potential options:

  1. Immediate solution: increase the limits for your org (by buying more credits, reaching out to OpenAI support, etc.... but IMO Codex should work with Tier 1 limits out of the box)
  2. Throttle Codex's requests to respect Tier 1 rate limits (maybe a worthwhile temporary fix for UX, but slows it down for everyone)
  3. OpenAI handles requests originating from Codex differently (a special key with different rate limits, for example)
r0wl · 1 year ago

Same issue here. Have seen multiple closed issues stating that the issue has been resolved, but issue is persisting.

pascudder · 1 year ago

@ashish01 @calvinlacock @r0wl I have a fix working for me here: https://github.com/pascudder/codex

jonchurch contributor · 1 year ago

dupe of https://github.com/openai/codex/issues/157

marciosete · 1 year ago

Seriously? My first experience of Codex was a Joke. First prompt, crash!

[Error]: Rate limit reached for gpt-4.1 in organization org- on tokens per min (TPM): Limit 30000, Used 26988, Requested 5783. Please try again in 5.542s. Visit https://platform.openai.com/account/rate-limits to learn more.

Yamilquery · 1 year ago
@ashish01 @calvinlacock @r0wl I have a fix working for me here: https://github.com/pascudder/codex

What did you change? It works amazingly!

wbraswell · 1 year ago

@tibo-openai
STILL NOT FIXED!!!
Lots of bugs open for this one issue?!?
https://github.com/openai/codex/issues?q=is%3Aissue%20state%3Aopen%20rate%20limit

tibo-openai collaborator · 1 year ago

Should be fixed in latest release, please install 0.1.2504221401 and re-open if this is still an issue you encounter.

Yamilquery · 1 year ago
Should be fixed in latest release, please install 0.1.2504221401 and re-open if this is still an issue you encounter.

Excellent, great news. Thank you, @tibo-openai.

I confirmed, it's working now.