Skip to content

Selected model is at capacity. Please try a different model. Keeps appearing; my pro x20 account is unusable, with 100% of my weekly quota remaining #43722

Open

Description

@q794464425

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

26.901.51231

What subscription do you have?

pro x20

What platform is your computer?

Microsoft Windows NT 10.0.22000.0 x64

What issue are you seeing?

Selected model is at capacity. Please try a different model. 一直出现,pro x20账号根本用不了,周额度还剩100%
之前都用的没问题的,就昨天和今天这两天一直弹Selected model is at capacity. Please try a different model
账号根本用不了

What steps can reproduce the bug?

Feedback ID: 01a07f09-210a-7840-90a6-bc2e08e1be87

What is the expected behavior?

Selected model is at capacity. Please try a different model. 不要一直出现,账号我能正常用,任务能正常执行完

Additional information

No response

Activity

  1. added
    appIssues related to the Codex desktop app
    on Sep 8, 2026
  2. added
    bugSomething isn't working
    rate-limitsIssues related to rate limits, quotas, and token usage reporting
    on Sep 8, 2026
  3. changed the title [-]Selected model is at capacity. Please try a different model. 一直出现,pro x20账号根本用不了,周额度还剩100%[/-] [+]Selected model is at capacity. Please try a different model. Keeps appearing; my pro x20 account is unusable, with 100% of my weekly quota remaining[/+] on Sep 8, 2026
  4. github-actions commented on Sep 8, 2026

    @github-actions
    Contributor

    English translation:

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

    26.901.51231

    What subscription do you have?

    pro x20

    What platform is your computer?

    Microsoft Windows NT 10.0.22000.0 x64

    What issue are you seeing?

    Selected model is at capacity. Please try a different model. Keeps appearing; my pro x20 account is completely unusable, with 100% of my weekly quota remaining.
    Everything worked fine before, but yesterday and today, Selected model is at capacity. Please try a different model has been popping up constantly.
    I cannot use my account at all.

    What steps can reproduce the bug?

    Feedback ID: 01a07f09-210a-7840-90a6-bc2e08e1be87

    What is the expected behavior?

    Selected model is at capacity. Please try a different model. Should not keep appearing. I should be able to use my account normally, and tasks should run to completion normally.

    Additional information

    No response

  5. medetasi commented on Sep 8, 2026

    @medetasi

    same

  6. coderDJing commented on Sep 8, 2026

    @coderDJing

    同样遇到此问题,已持续两天。\n\n我有 4 个 Plus 账户:其中 2 个完全正常,另外 2 个持续报 Selected model is at capacity. Please try a different model.。异常账户偶尔能执行少数命令,随后又立刻报同一错误。\n\n同一设备、同一时间、相同使用方式下出现这种账户间差异,似乎更像账户级的容量路由、资格/状态同步或服务端分流问题,而不是整体模型容量不足。请协助排查。

  7. cixiangtao commented on Sep 8, 2026

    @cixiangtao

    同样遇到此问题,已持续两天。\n\n我有 4 个 Plus 账户:其中 2 个完全正常,另外 2 个持续报 Selected model is at capacity. Please try a different model.。异常账户偶尔能执行少数命令,随后又立刻报同一错误。\n\n同一设备、同一时间、相同使用方式下出现这种账户间差异,似乎更像账户级的容量路由、资格/状态同步或服务端分流问题,而不是整体模型容量不足。请协助排查。

    你这几个账号都是什么区,付款方式一样吗

  8. q794464425 commented on Sep 8, 2026

    @q794464425
    Author

    有人要去Twitter骂Tibo的吗

  9. coderDJing commented on Sep 8, 2026

    @coderDJing

    同样遇到此问题,已持续两天。\n\n我有 4 个 Plus 账户:其中 2 个完全正常,另外 2 个持续报 Selected model is at capacity. Please try a different model.。异常账户偶尔能执行少数命令,随后又立刻报同一错误。\n\n同一设备、同一时间、相同使用方式下出现这种账户间差异,似乎更像账户级的容量路由、资格/状态同步或服务端分流问题,而不是整体模型容量不足。请协助排查。

    你这几个账号都是什么区,付款方式一样吗

    三个号菲区,其中一个正常,正常的那个号是周额度,剩下两个不正常的是5h额度,此外一个朋友的号,欧元区,5h额度,一切正常

  10. cixiangtao commented on Sep 8, 2026

    @cixiangtao

    同样遇到此问题,已持续两天。\n\n我有 4 个 Plus 账户:其中 2 个完全正常,另外 2 个持续报 Selected model is at capacity. Please try a different model.。异常账户偶尔能执行少数命令,随后又立刻报同一错误。\n\n同一设备、同一时间、相同使用方式下出现这种账户间差异,似乎更像账户级的容量路由、资格/状态同步或服务端分流问题,而不是整体模型容量不足。请协助排查。

    你这几个账号都是什么区,付款方式一样吗

    三个号菲区,其中一个正常,正常的那个号是周额度,剩下两个不正常的是5h额度,此外一个朋友的号,欧元区,5h额度,一切正常

    大概率是了,我也是菲区20x,已经无法使用了。而且我这边基本都是菲区炸了。看其他issues似乎新加坡区也有这个问题。但是旁边美区账户就没有问题。

  11. q794464425 commented on Sep 8, 2026

    @q794464425
    Author
    我的是美国的账号也一样
  12. Ideora2026 commented on Sep 8, 2026

    @Ideora2026

    same

  13. xiexiaoepng commented on Sep 8, 2026

    @xiexiaoepng

    PRO X20 same

  14. chen9071870-spec commented on Sep 8, 2026

    @chen9071870-spec

    菲区PRP X20 same

  15. Halary-wangqi commented on Sep 8, 2026

    @Halary-wangqi

    same question

  16. alexandrawallace commented on Sep 8, 2026

    @alexandrawallace

    so crazy, i cant to work now

  17. canadaeee commented on Sep 10, 2026

    @canadaeee

    Additional reproduction from another ChatGPT Pro user (Sep 10, 2026):

    • Codex Desktop repeatedly returns: Selected model is at capacity. Please try a different model.
    • The account still has substantial remaining usage/quota, so this does not appear to be a usage-limit exhaustion case.
    • Codex's built-in Test Connection succeeds (连接正常,我已收到你的消息。), which suggests basic network/auth connectivity is healthy.
    • The failure reproduces even in a trivial fresh prompt: 1+1=?, which immediately returns the same capacity error.
    • Switching the selected model from GPT-6 Astra to GPT-5.6 Sol does not resolve it; the same error continues.
    • The problem therefore looks more like an account/region/model-routing capacity issue in Codex rather than a project-size, context-length, or local connectivity problem.

    This currently makes Codex effectively unusable for the affected account. Please investigate model-serving/routing capacity for affected Pro accounts.

  18. canadaeee commented on Sep 10, 2026

    @canadaeee

    Additional reproduction from another ChatGPT Pro user (Sep 10, 2026):

    • Codex Desktop repeatedly returns: Selected model is at capacity. Please try a different model.
    • The account still has substantial remaining usage/quota, so this does not appear to be a usage-limit exhaustion case.
    • Codex's built-in Test Connection succeeds (连接正常,我已收到你的消息。), which suggests basic network/auth connectivity is healthy.
    • The failure reproduces even in a trivial fresh prompt: 1+1=?, which immediately returns the same capacity error.
    • Switching the selected model from GPT-6 Astra to GPT-5.6 Sol does not resolve it; the same error continues.
    • The problem therefore looks more like an account/region/model-routing capacity issue in Codex rather than a project-size, context-length, or local connectivity problem.

    This currently makes Codex effectively unusable for the affected account. Please investigate model-serving/routing capacity for affected Pro accounts.

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 reporting

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions