Skip to main content
Use Gemini models in BOR with a Google AI / Gemini API key.

​
Setup

  1. Get a key from Google AI Studio (linked from onboarding).
  2. In onboarding (or provider Settings), pick Google Gemini, paste your key, choose a model and a reasoning effort.

​
Models

The current list offered in BOR includes Gemini 3.5 Flash (recommended default), Gemini 3.1 Pro, Gemini 3.1 Flash Lite, Gemini 2.5 Pro, Gemini 2.5 Flash, and Gemini 2.5 Flash Lite. Ids rotate — the picker shows the live list.

​
Notes

  • Gemini models are vision-capable, so screenshot-driven features work.
  • Image generation uses Imagen 4 with the same key.
  • Reasoning effort (Off–Max) maps to Gemini’s thinking budget.

​
Troubleshooting

  • API key invalid / permission — check the key and that the Generative Language API is enabled for it.
  • 404 model — retired id; pick a current Gemini model.
  • See Troubleshooting.