`429 Too Many Requests` somehow
Resolved 💬 7 comments Opened Feb 8, 2026 by Gusarich Closed Feb 9, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of Codex CLI is running?
0.98.0
What subscription do you have?
Pro
Which model were you using?
gpt-5.3-codex
What platform is your computer?
Darwin 25.1.0 arm64 arm
What terminal emulator and version are you using (if applicable)?
Zed
What issue are you seeing?
exceeded retry limit, last status: 429 Too Many Requests, request id: da9f38d2-62f4-4d8a-9b66-f1ac1c67b087
exceeded retry limit, last status: 429 Too Many Requests, request id: 807b8cc6-b61e-41c1-81e6-8529a8ebfe66
What steps can reproduce the bug?
Run 25 subagents
What is the expected behavior?
No error :)
Additional information
It was working fine in past weeks with that many subagents (and even more), but for some reason today it throws rate limits ???
7 Comments
If this happens again, please use the
/feedbackslash command to upload your logs and post the thread ID here. Without logs, we won't be able to diagnose.This is likely because you're running 25 subagents. This may produce enough requests that it will look like a DDoS attack to our backend. That could result in 429s. By default, we cap the number of agents at 6 for this reason. If you're running 25, you'll likely hit this problem.
That’s sad :(
I want to clarify that in my case, I am seeing the same 429 Too Many Requests behavior without enabling the Sub-agents option at all.
@patricksuo, then you're likely seeing a different issue. If you see it again, please use the
/feedbackcommand to upload your logs and session details and open a new bug.I'm going to close this issue as resolved.
Did you solve this? I'm getting the same thing even though I'm far below my rate limits
same issue