Skip to content
CC Switch WikiUnofficial Community Wiki

Configured service tier `priority` is not advertised - Codex

Quick fix

Temporarily editing the model catalog can restore Priority requests, but regeneration overwrites it; no verified permanent solution is available.

Symptom

Section titled “Symptom”
Error output
Configured service tier `priority` is not advertised as supported for model `gpt-5.6-sol` and will be omitted from requests.

Cause

Section titled “Cause”

In CC Switch 3.16.5, Codex's third-party model catalog `cc-switch-model-catalog.json` unconditionally writes `additional_speed_tiers` and `service_tiers` as empty arrays. Codex therefore does not declare `priority` support and removes the `service_tier` parameter from actual `/responses` requests.

The reporter's temporary manual edit restores this declaration, but CC Switch overwrites it when switching Providers or resaving a Provider or model mapping. The maintainer confirmed this is the same issue as #5234 and said there is not yet a Provider- or model-level override; closing this issue was only to consolidate discussion, not to indicate a fix.

Fix

Section titled “Fix”

  1. Temporarily edit the generated model catalog to add Fast/Priority declarations for the target model. This change will be overwritten when switching Providers or resaving a Provider or model mapping.

    ~/.codex/cc-switch-model-catalog.json
    "additional_speed_tiers": ["fast"],
    "service_tiers": [
      {
        "id": "priority",
        "name": "Fast",
        "description": "Priority processing"
      }
    ]

  2. To follow up or report cases that still reproduce after an upgrade, comment in the maintainer-designated #5234 discussion; the original post does not provide a verified permanent solution.

Affected Versions

Section titled “Affected Versions”
ToolCodex
Version受影响：3.16.5
PlatformsWindows

Source Issues

Section titled “Source Issues”

This page is distilled from 1 real issues

FAQ

Section titled “FAQ”

(No FAQ yet)

Section titled “Related problems”
ChatGPT authentication fails with global proxy enabled - CodexUpgrade cc-switch to v3.16.4+ and enter a working proxy address under 「设置 → 路由 → 全局出站代理」, then retry Codex/ChatGPT authentication.3 issues mergedtruncation_policy.limit hardcoded to 10000 limits CodexIn cc-switch, manually set truncation_policy.limit in cc-switch-model-catalog.json to the model's actual context length as a temporary fix.9 issues mergedThe Gemini CLI reading the project .env breaks cc-switchWrap the gemini command in PowerShell to load the ~/.gemini/.env environment variables by hand.2 issues merged

This is an unofficial community wiki with no affiliation to the cc-switch authors or the project itself. Its content is compiled from the project's public GitHub issues. This site distributes no software.