Skip to content

Selected model is at capacity. #53256

Open
Open
Selected model is at capacity.#53256
Labels
CLIIssues related to the Codex CLIbugSomething isn't workingrate-limitsIssues related to rate limits, quotas, and token usage reporting

Description

@ythere-y
ythere-y
opened on Oct 12, 2026

What version of Codex CLI is running?

codex-cli 0.162.0

What subscription do you have?

20x Pro

Which model were you using?

gpt-6.1-sol medium

What platform is your computer?

Linux 6.6.98-40.6.tl4.x86_64 x86_64 x86_64

What terminal emulator and version are you using (if applicable)?

No response

Codex doctor report



What issue are you seeing?


Always response with "Selected model is at capacity. Please try a different model."


What steps can reproduce the bug?


Uploaded thread: 01a12df3-c1e6-7940-adce-57af05774b6e


What is the expected behavior?


No response


Additional information


No response
Activity
  1. ythere-y
    added 
    bugSomething isn't working
     on Oct 12, 2026
  2. github-actions
    added 
    CLIIssues related to the Codex CLI
     
    rate-limitsIssues related to rate limits, quotas, and token usage reporting
     on Oct 12, 2026
  3. github-actions commented on Oct 12, 2026 
    @github-actions
    github-actionsBot
    on Oct 12, 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. kejian-tong commented on Oct 12, 2026 
    @kejian-tong
    kejian-tong
    on Oct 12, 2026
    Image
  5. amibars commented on Oct 12, 2026 
    @amibars
    amibars
    on Oct 12, 2026 – with ChatGPT Codex Connector
    Adding a Windows desktop reproduction of this issue (October 12, 2026):
    

      

    • Model: GPT-6.1 Sol, High reasoning.
      • 

    • Environment: Windows desktop coding interface.
      • 

    • Impact: An existing long-running coding session has been blocked for 30+ minutes, with at least six consecutive failures. Retrying does not get the model running.
      • 

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

    • Additional failure: Automatic remote context compaction also fails with Error running remote compact task: Selected model is at capacity. Please try a different model. The UI repeatedly reports interrupted compaction ("Оптимизация прервана").
      • 

    

    This is not just an occasional rejected prompt: the capacity errors repeatedly interrupt an active development workflow and prevent context compaction in the same thread. The preceding local command/tool steps did execute, but subsequent model requests and remote compaction fail.
    

    Could the team investigate GPT-6.1 Sol capacity/request routing and the remote compaction failure path? I can provide sanitized screenshots or diagnostic details if needed.
  6. sn0wm1n commented on Oct 15, 2026 
    @sn0wm1n
    sn0wm1n
    on Oct 15, 2026
    same，01a1397a-d3f7-7333-91c8-4ab5bd80eb94
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
    CLIIssues related to the Codex CLIbugSomething 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