Codex CLI recommends gpt-5.4, then fails with 'Selected model is at capacity' despite available quota
Resolved 💬 30 comments Opened Apr 7, 2026 by debugger-net Closed Apr 7, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
Codex CLI GPT-5.4 Capacity Incident Report
Date: 2026-04-07
Reporter context: ChatGPT-authenticated Codex CLI user
Summary
The user was running Codex CLI with gpt-5.4 after Codex surfaced an upgrade path fromgpt-5.3-codex to gpt-5.4. Despite the user's report that 5-hour and weekly Codex
quota remained largely available, a turn failed with:
Selected model is at capacity. Please try a different model.
This appears to be a model-capacity/admission failure rather than quota exhaustion.
Local evidence
- CLI version:
codex-cli 0.118.0 - Auth mode:
Logged in using ChatGPT - Project config model:
gpt-5.4 - Global Codex host config model:
gpt-5.4 - Upgrade notice persisted locally:
~/.codex-host/config.tomlcontains:[notice.model_migrations]"gpt-5.3-codex" = "gpt-5.4"~/.codex-host/models_cache.jsoncontains upgrade text:Introducing GPT-5.4You can always keep using GPT-5.3-Codex if you prefer.- Capacity error log:
~/.codex-host/log/codex-tui.log- Timestamp:
2026-04-07T13:41:04.538491Z - Message:
Turn error: Selected model is at capacity. Please try a different model.
Reproduction notes
- A later minimal request using the same ChatGPT-authenticated Codex CLI and the same
gpt-5.4 model succeeded.
- A minimal request using
gpt-5.3-codexalso succeeded. - This suggests a transient
gpt-5.4capacity/admission problem, not a persistent
account-wide quota exhaustion.
Why this is problematic
- The product encouraged migration from
gpt-5.3-codextogpt-5.4. - The user is on a paid tier and reported substantial remaining quota.
- The failure mode did not explain whether this was:
- a quota problem,
- an abuse/security restriction,
- a temporary model-capacity shortage, or
- a workspace/account entitlement mismatch.
- Public documentation does not disclose the model-capacity priority order for Pro,
Business, Enterprise, or Edu users in Codex CLI.
Requested clarifications from OpenAI
- For this incident, was the failure caused by:
- temporary model capacity,
- an entitlement routing issue,
- an abuse guardrail,
- account security review, or
- another internal policy?
- Which entitlement path was actually applied to this local Codex CLI session?
- personal Pro
- Business workspace
- Enterprise/Edu workspace
- some other ChatGPT-linked path
- If this was capacity-related, what priority policy applied?
- Why was a user with available quota shown a model-capacity failure instead of a more
explicit explanation?
- If
gpt-5.4is promoted as the preferred upgrade fromgpt-5.3-codex, what
reliability expectation should users have in Codex CLI?
Public documentation reviewed
- Using Codex with your ChatGPT plan
- https://help.openai.com/en/articles/11369540-using-codex-with-your-chatgpt-plan
- GPT-5.3 and GPT-5.4 in ChatGPT
- https://help.openai.com/en/articles/11909943-gpt-53-and-54-in-chatgpt
- Troubleshooting Model Feature Access Issues
- https://help.openai.com/en/articles/10258669-troubleshooting-model-feature-access-issues
Constraints encountered while attempting submission
- The official support path exposed in the Help Center is the
Chat nowwidget or
phone support.
- From this terminal environment, the authenticated Help Center chat widget could not be
programmatically opened and submitted end-to-end.
30 Comments
This isn't a rate limiting message — that is, it's not specific to your account. This message indicates that we are out of capacity on this model.
But instead cutting off running commands. Isnt it better to deny new requests?
I recomend using -fast
what about enqueuing the request in this case? This message break CLI workflows, among others.
nice. upgraded to PRo and got it today few times. What is a solution for the customers? it has to retry, i do not want to do manual continue promts or having loose the context.
Ran into this, too. That's disappointing.
I also encountered this on Tarfia Plus, I don't feel like buying it anymore
+1 同样出现这个问题 工作高峰期 已切codex 5.3
me, too
First day of using my Chatgpt Plus account via Codex Cli on Antigravity.
had 3 to 4 conversations to set context and 1 completed task before I see this message.
Next best alternative model to continue btw ?
It looks like a codex issue - every model I try, I get this error and judging from the rate of messages here in the last 5 minutes - it may be a transient problem.
I wouldn't mind as much if it were free, but for a paid service it's frustrating, particularly because it's designed for workers.
Repeated
Selected model is at capacity. Please try a different model.errors during active sessions.Details:
Yep, also running into capacity issues here.
You should stop new requests rather than cutting off people work half way, if that is a capacity issues, and we are not free user, we paid for it. Of course unless you have other VVVIP, that is higher priority than us, that need to use the capacity ...
Exactly the same issue. Paying for Pro and seeing "Selected model is at capacity. Please try a different model." for 5.3-Codex. I agree that this should not appear half-way through the work but stop new requests.
Also getting this error on Codex version 5.4 Windows:
Selected model is at capacity. Please try a different model.
+1
Top-tier service... if you’re looking for a masterclass in how to ignore paying customers
Charging Money for a service - makes YOU responsible to fullfill the contract with your customer. Get your shit together.
I had the same problem temporarily, but it’s working now.
Interesting. Same here. What is it with today? Can't imagine gaining 10k more users over night.. A server issue? It's the same for me even when going back to 5.3.
+1
same issue, when will these ai's run in our own devices? Or are we gonna have these same issues over and over again?
It's been happening frequently over the past hour, and what's frustrating is getting interrupted in the middle of a task. Honestly, it might be easier to accept if it just didn't work from the start.
+1
Same here. First time this popped up. Pro@5x, 5h 91%, Weekly 69%
The suggestion to switch to a different (lower) model is not acceptable while working on a task and risk quality degradation. This means we have to compensate for the degradation later, burning more tokens and time.
<img width="647" height="110" alt="Image" src="https://github.com/user-attachments/assets/a4716937-5036-4e35-845c-e3378e2a8949" /> ，截止到2026年5月6日，该问题依旧存在
貌似开启fast就不会出现这个问题
same issue in gpt-5.5 today