I still feel there is no sure shot way to build an abstraction yet. Probably that is why Loveable decided to build on Gemini AI rather than giving options of choosing model. On the other hand I like Pydantic AI framework and got myself a decent working solution where my preference is to stick with cheaper models by default and only use expensive only in cases where failure rate is too high.
I feel like there's always that "one guy" who has a preference and asks for an option to choose, and, it's a way for developers to offload the decision. You can't be blamed for the wrong one if you put that decision on the user.
Tbh I agree with your approach and use it when building stuff for myself. I'm so over yak shaving that topic.
