Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in?

There is no best model, only a best model for your task at your price: test the top two or three on your own real examples rather than trusting benchmark headlines. Design your code so the model is a swappable config value (a thin gateway or SDK abstraction does this), because prices and leaders change every few months. Open-source models make sense once you have scale, strict data constraints, or a narrow task; for most first features a hosted API wins on speed to ship.

A quick orientation. The real value is below: resources worth your time, from people who've actually done it.