Issues with Model Rate limits

[PtradeLLC]

Select Topic Area

Question

GitHub Feature Area

Actions

Body

Can someone please explain this to me as I couldn't get an answer fast enough from Github support which is extremely frustrating since I am a paying subscriber and all. So I recently signed my team for the Copilot subscription, and all seemed to be well until we received the following message:

You have exceeded your premium request allowance. We have automatically switched you to GPT-4.1 which is included with your plan. [Enable additional paid premium requests](vscode-file://vscode-app/Applications/Visual%20Studio%20Code.app/Contents/Resources/app/out/vs/code/electron-browser/workbench/workbench.html) to continue using premium models.

Cool. We then updated the premium request allowance (as shown in the attached image), hoping that once that is done we'd be able to at least continue using Copilot as expected but the message continue to persist. We are even open to upgrading our account to a higher subscription plan to avoid this mess but found out that Github is like Times square of the web as the resources to upgrade have us going in circles from page to page with no direct link.

This is extremely frustrating to have to wait to resolve such issues as a paying customer.

I can imagine someone else went through this, can you share how you were able to resolve this?

[pratikrath126]

Hi PtradeLLC, sorry for the frustration. This usually means the Copilot extension is still using cached quota info. First, sign out of Copilot in VS Code (Cmd+Shift+P → 'Copilot: Sign Out'), then sign back in with your GitHub account that has the subscription. Restart VS Code after signing in. Also verify with your organization admin that your Copilot seat is assigned and the billing is complete. If the message still appears after 15-20 minutes, contact GitHub Support with your org name and user ID.