"OpenAI rejected the request"

I set export OPENAI_API_KEY= and ran the codex cli with a simple prompt "read the README.md" and ran into this error:

    ⚠️  OpenAI rejected the request (request ID: req_13e38c243f89126dd24093d2e4892535). Please verify your settings and
    try again.

Is there any way to debug this?

Running into this too, and have access to all models.

Ran into this exact issue

Can confirm

++ Same issue

Surely there must be a step somewhere where I can provide my API key? The README.md just says to run the npm command and there's "zero configuration" from there. How could that be? Is OpenAI providing this service for free?

In the OP's description they mention OPENAI_API_KEY because it's only in the Non‑interactive / CI mode section. Should we have that in our environment anyway?

I have that but still get this result.

same

as well

Happening here as well, maybe still rolling out? I'm on tier 5 and have access via the API and playground.

same pinch.

samesies! <3 super pumepd though!

it prob cant find the key because workdir is defaulted to "~"

anyone see how to specify workdir?

│ localhost session: * │ ↳ workdir: ~ │ ↳ model: o4-mini │ ↳ approval: suggest

wrong issue, but just run codex on the workdir you want, ex:
cd code/react/foo; codex

This is the issue actually:

    system
    ⚠️  OpenAI rejected the request (request ID: req_a057493e36bb3dda8a2fe4646b7d4cb0): 400 Your organization must be verified to generate reasoning summaries. Please go to: 
https://platform.openai.com/settings/organization/general and click on Verify Organization.. Please verify your settings and try again.

https://platform.openai.com/settings/organization/general

I made a PR to fix this. #23

Same problem here!

Hey! 👋

So just a thought — the default model used by the CLI is o4-mini, which I think might not be fully rolled out to everyone yet. If your API key doesn’t have access to that model, that could explain the rejection error you’re seeing.

You might want to try running the /model command in the CLI and picking something like gpt-4.5 instead — basically any model you know you have access to — and see if that helps.

Not totally sure that’s the issue, but worth trying! Let me know if that works for you.

anyone figure out how to get reasoning level to work?

Fix was fixed earlier today, please open new issues for other things and thanks for being patient!

same only the o4-mini-[date-slug] works for me!

docs(changelog): note clipboard image paste support and auto-close #10

Strengthen linker runtime verification

feat(orchestrator): Phase 3 crate skeleton + types + trait stubs

fix(tui): keep thread ops non-fatal when the app-server request fails

Repo health ratchet gates, PathUri migration epic, offline changelog …

fix(rig-bridge): tool-call state machine + custom tool round-trip

Compaction V2: 時系列注記で最新の message を示し、開始手順を繰り返さないよう伝える

Navigation Menu

Repository navigation

"OpenAI rejected the request" #10

22 remaining items

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

"OpenAI rejected the request" #10

Description

Activity

LuciferMornens commented on Apr 16, 2025

shobhitic commented on Apr 16, 2025

ndisalvio3 commented on Apr 16, 2025

maheshrijal commented on Apr 16, 2025

adamjgrant commented on Apr 16, 2025

justinechang39 commented on Apr 16, 2025

rasdani commented on Apr 16, 2025

MadcowD commented on Apr 16, 2025

johanbaath commented on Apr 16, 2025

DhrubaPatra commented on Apr 16, 2025

bradennapier commented on Apr 16, 2025

EverStarck commented on Apr 16, 2025

MadcowD commented on Apr 16, 2025

leandroz commented on Apr 16, 2025

cruffinoni commented on Apr 16, 2025

22 remaining items

adityamcodes commented on Apr 16, 2025

tibo-openai commented on Apr 16, 2025

kohl00 commented on Apr 16, 2025

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions