Last week, I started working on a new side-project. It’s a standard React app partly made up of run-of-the-mill CRUD views—a perfect fit for LLM-assisted programming. I reasoned that if I could get an LLM to quickly write the boring code for me, I’d have more time to focus on the interesting problems I wanted to solve.
I’ve pretty much settled on Claude Code as my coding assistant of choice, but I’d been hearing great things about Google’s Gemini 3 Pro. Despite my aversion to Google products, I decided to try it out on my new codebase.
I already had Gemini CLI installed, but that only gave me access to Gemini 2.5 with rate limits. I wanted to try out Gemini 3 Pro, and I wanted to avoid being rate limited. I had some spare cash to burn on this experiment, so I went looking for ways to pay for a Gemini Pro plan, if such a thing existed.
Thus began my grand adventure in trying to give Google my money.
What is a Gemini, really?
The name “Gemini” is so overloaded that it barely means anything. Based on the context, Gemini could refer to:
The chatbot available at gemini.google.com.
The mobile app that lets you use the same Gemini chatbot on your iPhone or Android.
The voice assistant on Android phones.
The AI features built into Google Workspace, Firebase, Colab, BigQuery, and other Google products.
... continue reading