Repository navigation
Complaint from a $200/month Pro user—99% of quota remains, but Codex keeps reporting “Selected model is at capacity,” severely disrupting normal use #46143
Description
What version of the Codex App are you using (From “About Codex” dialog)?
Powered by Codex & OWL 版本 26.911.61220 发布于 2026年9月17日
What subscription do you have?
200$pro
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
我是每月支付200美元的ChatGPT Pro用户。本月使用Codex时频繁、连续出现错误，已严重影响正常使用。2026年9月16日仍在反复发生，并非偶发的一次失败。
我提供的额度截图显示：
通用每周使用限额剩余99%；
GPT-5.3-Codex-Spark的5小时和每周使用限额均剩余100%。
连续报错截图显示：
“Selected model is at capacity. Please try a different model.”
此外，远程上下文压缩也出现错误：
“Error running remote compact task: Selected model is at capacity. Please try a different model.”
请注意：截图中的Spark是额度页面列出的项目，不代表已确认它就是报错请求使用的模型。请结合实际请求日志排查。
我的核心问题是：付费订阅仍有效、页面显示大量额度可用，但服务持续无法正常使用。请不要在未核实日志的情况下，将此问题简单按额度耗尽处理，或只建议购买额外额度、等待额度重置。
请将此问题转交人工支持及相关工程团队，并答复：
- 连续失败的具体原因，是否涉及模型容量、请求路由、账号限流或远程上下文压缩服务异常。
- 恢复正常使用的处理方案及预计时间；若暂时无法给出时间，请明确说明。
- 对于已付费但持续无法正常使用的受影响时段，是否提供订阅延期、费用减免或其他补偿。
请提供可追踪的工单编号，不要仅以通用排障模板结束处理。
What steps can reproduce the bug?
只要正常运行codex就能够复现，并且是高频率出现，已经完全无法正常使用了。一直报Selected model is at capacity. Please try a different model.错误。
What is the expected behavior?
No response
Additional information
No response
Activity
[-]Pro 200美元/月用户投诉——额度剩余99%，Codex仍持续报“Selected model is at capacity”，严重影响正常使用[/-][+]Complaint from a $200/month Pro user—99% of quota remains, but Codex keeps reporting “Selected model is at capacity,” severely disrupting normal use[/+]github-actions commentedon Sep 17, 2026
English translation:
What version of the Codex App are you using (From “About Codex” dialog)?
Powered by Codex & OWL version 26.911.61220 Released on September 17, 2026
What subscription do you have?
200$pro
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
I am a ChatGPT Pro user paying $200 per month. This month, I have encountered frequent, repeated errors while using Codex, severely disrupting normal use. They were still occurring repeatedly on September 16, 2026; this is not an isolated failure.
The quota screenshot I provided shows:
99% of the general weekly usage limit remains;
100% of both the 5-hour and weekly usage limits for GPT-5.3-Codex-Spark remains.
The screenshots of repeated errors show:
“Selected model is at capacity. Please try a different model.”
In addition, remote context compaction also encounters an error:
“Error running remote compact task: Selected model is at capacity. Please try a different model.”
Please note: Spark appears in the screenshot because it is listed on the quota page. This does not mean it has been confirmed as the model used by the failing requests. Please investigate using the actual request logs.
My core issue is that my paid subscription is still active and the page shows plenty of available quota, yet the service persistently fails to function normally. Please do not simply treat this as exhausted quota without checking the logs, or only suggest purchasing additional quota or waiting for the quota to reset.
Please escalate this issue to human support and the relevant engineering teams, and respond with:
Please provide a trackable support ticket number, and do not close the case with only a generic troubleshooting template.
What steps can reproduce the bug?
Simply running codex normally reproduces the issue, and it occurs so frequently that normal use has become completely impossible. It keeps reporting the error Selected model is at capacity. Please try a different model.
What is the expected behavior?
No response
Additional information
No response
github-actions commentedon Sep 17, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action