Selected model is at capacity

[nickzsb.nz]

Using gpt-5.4 is consistently showing me this message

[nickzsb.nz]

[bbu]

What is going on?

What is going on?

[EricGT]

Also see:

Codex (VS Code extension) stops working mid-session with "model at capacity" errors

Welcome to the forum! Thanks for reporting, specifically for giving an exact human readable error message, “Selected model is at capacity” Your issue has also been reported in this Discourse topic. You can discuss Codex-related issues here, but the official place to report them is the OpenAI Codex GitHub Issues. In doing a quick manual search of the open issues for “model at capacity” find The noted issue suggest using the Codex slash command /feedback but then goes on to note that it i…

[EricGT]

@bbu Welcome to the forum!

I see you have two other recent topics, are these all related?

Stream disconnected before completion

stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 8e867191-7bf3-4140-a9bb-0ffacdfdae1c in your message.

LLM error server_error codex

LLM error server_error: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID 9c1b2b92-4f9f-4b42-88dc-0ee54abc13f4 in your message.

[ZeroTheAbsolute]

I’m seeing this a ton today and it’s causing some major issues in long running workflows. Effort becomes shallow and tasks stop suddenly with no warning and a small hard to read message in a giant wall of text for a session that has been running for hours.

I have had to go back and correct major issues multiple times in the last 24 hours due to these effects. GPT 5.5 xHigh, Codex Desktop MacOS and Windows desktop both.

[h3o]

Same on Windows Codex App