Please fix the Gemini API verification workflow, as right now it’s trying to use a model for verification that Google no longer supports
{
"error": {
"code": 404,
"message": "models/gemini-1.0-pro is not found for API version v1beta, or is not supported for generateContent. Call ListModels to see the list of available models and their supported methods.",
"status": "NOT_FOUND"
}
}
it doesn’t matter what models are selected in the settings > models page, it’s trying to use that curl command under the hood which doesn’t work.
per Google AI Studio, this is the command they suggest:
"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=GEMINI_API_KEY"
Cursor is trying to call gemini-1.0-pro
which is depricated
please either let us either specify which model to use for verification or just let us put in an API key, and if it doesn’t work when we try to make a call, let us know then. it would be much easier to shoot out an error message on a bad API call than hardcoding a verification URL and hoping it doesn’t change in an industry that moves as fast as AI
if this doesn’t get fixed I’ll need to cancel my Cursor subscription as I have Gemini API access through my employer and they request that we use it for job-related work