Gemini 2.5 - Not Great - May Get Better

As far as I can tell and from what I have read the API from Google is not supporting the thinking functionality - Also it cannot use images…

If you want to try it anyway you can select it from Agent mode now - You will be charged at the premium rate though - To get around this you can use your own API key in settings, ignore the verify error - This is available in Ai Studio and is free - I think you have a 50 call per day limit though…

Basically, I tried a quick and easy ToDo app and it had errors - Not a good look!..

2 Likes

I also tried to check its strength and found it not completely obeyed the rule that I set in the cursor as the way Claude 3.7 Sonnet followed. It may be because this model is too new, so Cursor has not “domesticate” it so we can control it with Rule for AI.

Regarding the thinking, while it does have a thinking step, Gemini doesn’t send these tokens to us, so we can’t show them within Cursor yet.

2 Likes