Custom Models Not Loading in Copilot Chat, HTTP still requesting Copilot GPT4.1

[ZHLONG-CN]

Does this issue occur when all extensions are disabled?: Yes

• VS Code Version: 1.101.2
• OS Version: Windows 11 22H2

I change custom model to gemini, but I notice the http request still model Copilot GPT4.1

Me

hi

GitHub Copilot

Sorry, your request failed. Please try again. Request id: 60407e7f-c569-497f-a723-d17b9f1071c2

Reason: Canceled

LOG

2025-07-06 15:52:28.671 [trace] Resolving chat model
2025-07-06 15:52:28.671 [trace] Resolved chat model
2025-07-06 15:52:28.671 [trace] Building intent detector
2025-07-06 15:52:28.671 [trace] Resolving chat model
2025-07-06 15:52:28.671 [trace] Resolved chat model
2025-07-06 15:52:28.673 [trace] Built intent detector
2025-07-06 15:52:29.806 [info] Request ID for failed request: ad3ddfef-1bff-4971-b85e-82b0eb32ada7
2025-07-06 15:52:29.812 [debug] Resetting copilot token on HTTP error 402

HTTP REQUEST

POST https://api.individual.githubcopilot.com/chat/completions HTTP/2
host: api.individual.githubcopilot.com
content-length: 5186
authorization: Bearer ...
...
x-github-api-version: 2025-05-01
x-initiator: agent
x-interaction-id: da7161cb-f09e-43f5-b1f8-56d4f7355065
x-interaction-type: conversation-panel
x-request-id: ad3ddfef-1bff-4971-b85e-82b0eb32ada7
...

{"messages":[{"role":"system","content":"You are a helpful AI programming assistant to..."},{"role":"user","content":"hi"}],"model":"gpt-4o-mini","temperature":0.1,"top_p":1,"max_tokens":4096,"stop":[";"],"n":1,"stream":true}

HTTP RESPONSE

HTTP/2 402
cache-control: no-cache
content-security-policy: default-src 'none'; sandbox
content-type: application/json
...

{"error":{"message":"You have no quota","code":"quota_exceeded"}}

[vs-code-engineering]

This issue is a duplicate of #253136. Please refer to that issue for updates and discussions. Feel free to open a new issue if you think this is a different problem.