openai / openai/codex

Abnormal slowdown and faster usage consumption in Codex

Open
#46,249 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

app bug Linux performance rate-limits
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of the Codex App are you using (From “About Codex” dialog)?

26.911.61220

What subscription do you have?

ChatGPT Pro

What platform is your computer?

Linux 7.0.0-31-generic x86_64 x86_64

What issue are you seeing?

Over the last couple of days, Codex has been noticeably slower than usual for me.

This does not seem limited to a specific repository or a particularly complex task. In general, normal tasks are taking significantly longer to complete than they did before, with more time spent thinking or processing.

At the same time, I also have the impression that my usage/tokens are being consumed faster than usual, even though my workflow has not changed significantly.

I'm on ChatGPT Pro, and the overall experience currently feels noticeably degraded compared with my normal usage.

I understand that performance can vary depending on task complexity and system load, but the slowdown has been consistent enough to affect my productivity.

It would be helpful if the team could check whether there are any current performance issues, capacity constraints, or changes affecting Codex latency and usage consumption.

What steps can reproduce the bug?

Just general use.

What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The report names no repository file, test, or reliably reproducible task. Start by checking current Codex performance and usage behavior on the reported Linux environment, then compare it with the normal baseline across general tasks. Done means identifying a reproducible cause or confirming a documented service-side performance issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
linux, rust
Domain
cli, devtools, performance
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.