The cheapest Gemini LLM model is currently experiencing high demand.

[tuapuikia]

Last week, I could still use the cheapo model to run some automation tasks, but since yesterday, I feel like everyone is rushing to use the cheapest model instead of the Flash or Pro.

✕ [API Error: got status: INTERNAL. {"error":{"code":500,"message":"An internal error has occurred. Please retry or report in
https://developers.generativeai.google/guide/troubleshooting","status":"INTERNAL"}}]

10 requests, 10 failed when using gemini-2.5-flash-lite-preview-06-17 😅

No problem with Gemini 2.5 Flash and Pro models. What LLM model are you using in your daily tasks?

With my local hack, I am now able to switch models in the same session, but it's a bit annoying not to be able to use the cheapest model.