Appreciate the feedback!
1. There should be no need to create a project to use the Vertex Gemini API. I know Google AI Studio doesn't need a project, but that API is limited compared to Vertex API, which brings me to the next point.
2. There should be one unified API, not two! That'll help scale products with ease. Currently Google recommends using Google AI Studio API for simple projects and one-off scripts, and Vertex for "real" projects. No other competitor does this (look at OpenAI for instance).
3. The OpenAI compatibility layer isn't complete and doesn't support other Gemini features that only the Gemini API supports (e.g,. setting safety level).
4. Devs should need to install only one package to use Google Gemini. Please get rid of gauth.
5. The documentation on Gemini API is fragmented. Ironically, Googling "gemini api doc" doesn't lead to the page that discusses how to get started easily and quickly.
It's similar to how a bunch of projects get created whenever you use Apps Scripts.
Ideally what I want is this: I google "gemini api" and that leads me to a page where I can login using my Google account and see the API settings. I create one and start using it right away. No extra wizardry, no multiple packages that must be installed, just the gemini package (no gauth!) and I should be good to go.