Skip to content

[Windows] "Selected model is at capacity" for 6 consecutive days across all models and reasoning efforts (ChatGPT Plus) #46162

Open
Open
[Windows] "Selected model is at capacity" for 6 consecutive days across all models and reasoning efforts (ChatGPT Plus)#46162
Labels
appIssues related to the Codex desktop appbugSomething isn't workingrate-limitsIssues related to rate limits, quotas, and token usage reportingwindows-osIssues related to Codex on Windows systems

Description

@hxtao1001
hxtao1001
opened on Sep 17, 2026

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

26.911.7940.0 (OpenAI.Codex_26.911.7940.0_x64__2p2nqsd0c76g0); bundled CLI codex-cli 0.154.0-alpha.6.2

What subscription do you have?

ChatGPT Plus

What platform is your computer?

Windows 11 Pro, Build 26200, x64

What issue are you seeing?

Every normal turn fails with:

Turn error: Selected model is at capacity. Please try a different model.

This is NOT tied to one model or one reasoning effort. On 2026-09-17 alone I logged 52 of these errors in the normal conversation path (codex_core::session::turn).

What I tested today, all failing:

  • gpt-5.6-sol, reasoning_effort=high -> "at capacity"
  • gpt-5.6-sol, reasoning_effort=low -> "at capacity"
  • gpt-5.6-luna, reasoning_effort=high -> "at capacity" (11 consecutive failures in 70 seconds: 16:04:38 -> 16:05:48)

Totals from ~/.codex/logs_2.sqlite (115 failures in codex_core::session::turn over 6 days):
09-07: 2 | 09-08: 3 | 09-11: 23 | 09-12: 16 | 09-16: 35 | 09-17: 36 and counting

Raw log line (PII redacted):

session_loop{thread_id=}:submission_dispatch{otel.name="op.dispatch.turn_input" codex.op="turn_input"}:turn{otel.name="session_task.turn" model=gpt-5.6-luna codex.turn.reasoning_effort=high}:session_task.run:run_turn: Turn error: Selected model is at capacity. Please try a different model.

The retry button re-sends the same model, so it loops on the same error indefinitely.

What steps can reproduce the bug?

  1. Run the Codex desktop app on Windows (MSIX build 26.911.7940.0), signed in with a ChatGPT Plus account.
  2. Leave the defaults written to ~/.codex/config.toml: model = "gpt-5.6-sol", model_reasoning_effort = "high".
  3. Send any prompt in a normal conversation. The turn fails immediately with "Selected model is at capacity. Please try a different model."
  4. Switch the model to gpt-5.6-luna, and separately lower model_reasoning_effort to "low". Retry - same error on both.
  5. Press the retry/continue button repeatedly - same error, because it re-sends the same saturated model.
  6. Repeat on subsequent days - same result every day since 2026-09-07, at all hours of the day.

What is the expected behavior?

A paying ChatGPT Plus subscriber should be able to use Codex, or at minimum:

  1. The app should detect that the selected model is saturated and automatically fall back to an available model, instead of failing the whole turn.
  2. The retry button should not blindly re-send the same saturated model.
  3. The error should be distinguishable from an account-level or plan-level limit, and should carry the request id so support can trace it.
  4. There should be a status/incident surface so users can tell a capacity problem apart from a local misconfiguration.

I understand this is a capacity problem on OpenAI's side and I have already opened a support case for it. I am filing this here so there is a public record with concrete data.

Additional information

Environment: Windows 11 Pro Build 26200, ChatGPT.exe MSIX package OpenAI.Codex_26.911.7940.0_x64__2p2nqsd0c76g0, model_provider = "openai", auth_mode = "chatgpt".

Data source: ~/.codex/logs_2.sqlite, table logs, column feedback_log_body, filtered on '%at capacity%'.

Activity

  1. hxtao1001
    added
    appIssues related to the Codex desktop app
    on Sep 17, 2026
  2. github-actions
    added
    bugSomething isn't working
    windows-osIssues related to Codex on Windows systems
    rate-limitsIssues related to rate limits, quotas, and token usage reporting
    on Sep 17, 2026

  3. github-actions commented on Sep 17, 2026

    @github-actions
    github-actionsBot
    on Sep 17, 2026 – with GitHub Actions
    Contributor

    Potential duplicates detected. Please review them and close your issue if it is a duplicate.

    Powered by Codex Action

  4. Controller-H commented on Sep 17, 2026

    @Controller-H
    Controller-H
    on Sep 17, 2026

    Codex Desktop (Windows 11, ChatGPT Plus) - "Selected model is at capacity" on every model; allowance only 2% / 62% used

    Summary

    Since 2026-09-17 20:54 (UTC+8) every Codex turn on this account fails immediately with:

    Turn error: Selected model is at capacity. Please try a different model.

    Occasionally the same session also produces:

    Turn error: 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.

    This is effectively 100% of requests. The error appears on at least gpt-5.6-sol and gpt-5.6-luna in the same session, and the user reports the same result on every model available in the picker.

    This is not a quota problem on this account

    Response headers captured on the same account at 2026-09-17 13:05:47 UTC:

    x-codex-plan-type:              plus
x-codex-active-limit:           premium
x-codex-primary-used-percent:   2      (window: 300 min)
x-codex-secondary-used-percent: 62     (window: 10080 min)
x-codex-primary-reset-at:       1789662954  -> 2026-09-18 00:35:54 UTC+8
x-codex-secondary-reset-at:     1789805339  -> 2026-09-19 16:08:59 UTC+8
x-codex-credits-balance:        0
x-codex-credits-has-credits:    False
x-codex-credits-unlimited:      False

    The 5-hour window is 2% used and the 7-day window is 62% used. The account is not rate-limited, and requests on the same account were returning 200 OK at 13:05:47 to 13:06:12 UTC.

    This is not an auth or connectivity problem

    codex doctor (Codex CLI 0.155.0-alpha.2.6, windows-x86_64):

    • auth: configured; storage mode File; mode chatgpt; ChatGPT tokens present; no API key
    • websocket: connected (HTTP 101 Switching Protocols)
    • ChatGPT inference URL: reachable (HTTP 405)
    • state / log / goals / memories / queue / thread-history DBs: integrity ok
    • summary: 19 ok, 1 idle, 4 notes, 4 warn, 0 fail
    • Full redacted JSON report attached.

    Failing turns

    Local (UTC+8) UTC thread id turn id model
    2026-09-17 21:06:23 13:06:23 01a0af79-b1f1-78c2-ae18-10dd34396b92 01a0af79-b25f-7881-b560-c183db475d0c gpt-5.6-luna
    2026-09-17 21:06:23 13:06:23 01a0af79-8959-7cc0-98d5-ed577233ca66 01a0af79-b312-72b1-9ddc-10c67b4db866 gpt-5.6-sol
    2026-09-17 21:06:43 13:06:43 01a0af79-8959-7cc0-98d5-ed577233ca66 01a0af7a-028c-7ba3-aa51-5254696110e4 gpt-5.6-sol
    2026-09-17 21:07:23 13:07:23 01a0af79-8959-7cc0-98d5-ed577233ca66 01a0af7a-9b02-71d0-8910-57f96e983871 gpt-5.6-sol
    2026-09-17 21:09:47 13:09:47 01a0af79-8959-7cc0-98d5-ed577233ca66 01a0af7c-cdb4-7dc2-b6ef-9ea6a50b4de3 gpt-5.6-sol

    Request IDs captured around the failing turns

    2026-09-17 13:06:15 UTC  req_27bc99cd183241468c5c5281ae82322e
2026-09-17 13:06:24 UTC  req_3e15963b9aa94a6d8d1e6d39b560013c
2026-09-17 13:06:31 UTC  req_b878103808b24eed9cda54326b5ef19b
2026-09-17 13:07:20 UTC  req_45a2ad8cc4314aa38db270fc8e0c7ca7
2026-09-17 13:07:32 UTC  req_50be7ca747ab481e8356f7d1543be994
2026-09-17 13:09:53 UTC  req_1b13ea465b1f4173bd520727d3c1c3ad
2026-09-17 13:12:25 UTC  req_615c351bff8e4593a0b36ebd2afc3998

    Environment

    OS                  Windows 11 Home (CoreCountrySpecific), 10.0.26200, AMD64, zh-CN
Timezone            China Standard Time (UTC+8)
Codex Desktop       26.911.7940.0   (MSIX OpenAI.Codex_26.911.7940.0_x64__2p2nqsd0c76g0)
Release channel     26.911.61220
app-server / CLI    0.155.0-alpha.2.6
Auth mode           chatgpt (file-based, no API key)
wss endpoint        wss://chatgpt.com/backend-api/...   connected (HTTP 101)

    Already tried

    • Restarting the Codex Desktop app
    • Reinstalling / updating to the current version
    • Switching models in the picker (gpt-5.6-sol, gpt-5.6-luna, gpt-6-astra)
    • Verifying network access (inference endpoint reachable; websocket connects)
    • Verifying local state DB integrity (codex doctor, all ok)

    What I'm asking for

    1. Confirmation of whether this account is affected by the known account-level "Selected model is at capacity" defect.
    2. Clearing the server-side capacity state for this account, or a workaround.
    3. Any logging you need from my side - the attached codex-doctor-report.json plus the request IDs above should be sufficient to trace.

    For reference, this matches the following public reports and the official incident:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    appIssues related to the Codex desktop appbugSomething isn't workingrate-limitsIssues related to rate limits, quotas, and token usage reportingwindows-osIssues related to Codex on Windows systems

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions