Plataforma de gestión inteligente de solicitudes de IA que optimiza y distribuye consultas entre múltiples proveedores para evitar rate limits.

Repository: microsoft/vscode Author: digitarald This meta issue tracks scenarios where chat requests are blocked due to rate limiting. 👉 To get help with **premium request quota issues**, please comment in https://github.com/microsoft/vscode/issues/252230 . In case you experience repeated rate-limiting in GitHub Copilot, please reach out to GitHub Support: https://support.github.com/ Error message: > Sorry, your request was rate-limited. Please wait x minutes before trying again. Most users see rate limiting for preview models, like OpenAI’s `o1-preview` and `o1-mini`, which are rate-limited due to limited preview capacity. Another cause is higher request/token usage for agent mode, which is still in _preview_ partially of this capacity Service-level request rate limits ensure high service quality for all Copilot subscribers and should not affect typical or even deeply engaged Copilot usage. We are aware of some use cases that are affected by it. GitHub is iterating on Copilot’s rate-limiting heuristics to ensure it doesn’t block legitimate use cases. 👉 **Latest update** (Mar 10th, 2025), bringing more capacity online for Claude: https://github.blog/changelog/2025-03-06-onboarding-additional-model-providers-with-github-copilot-for-claude-sonnet-models-in-public-preview/