When I use Auto mode, does it chose model from all models or only from models that enabled in my settings? If I have only gemini flash and pro enabled will cursor choose between these two models in Auto or it will still go to disabled models?
Only the ones you have enabled in your Cursor Settings.
It cant go just by your 4 models, as your models are the most overloaded models today right after new launch 
Cursor team stated before in forum and in docs that the Auto used current premium models (not opus, o3) that are not overloaded. So GPT 4.1 is not a bad choice.
it does the same with i select Gemini models only. seems always defaults to 4.1. i am not to complain that 4.1 is bad, jsut trying to get some transparency into Auto mode
Right, thats what I meant with my previous comment to shed a a bit light on how the Cursor teams definition of Auto is playing out in the app.
Gemnini is also on the limit as some prefer Gemini and others want Claude
The question is why nobody uses 4.1 anymore, haha
Auto is designed to use a premium (1-request cost) model while ensuring a stable, reliable output! It’s best for people who don’t care for learning the intricacies of each model and also for working around model downtime and outages with the inference providers.
Due to how it works, it does not respect the list of models you have enabled, but should give you a consistent level of intelligence each time.
Not all models are consistent with their output style, I personally think it is bad not having a Auto-Option that DOES respect the approved models list, some users may want to only use Gemini 2.5 Pro and Flash 2.5 or Grok-3-Beta & Grok-3-Mini or Sonnet 4 & Sonnet 4 Thinking to keep things consistent but maintain a balance between a faster more performant model & a more advanced reasoning model for complex tasks…
1 Like