Gemini Decisions API
A Gemini API built to make quick yes/no, pick-one, and grading calls without generating any text, for developers building apps and agents.
Details
- Runs on a new model, Gemini Decision 1 (gemini-decision-1), which returns binary, categorical, or rubric-based decisions instead of written output
- Up to 1,000 questions can be evaluated in a single request, all against one shared input
- That shared input can be text, images, audio, video, or PDFs
- Priced at $0.10 per 1M input tokens with $0 for output tokens, since nothing is generated. Available now through the Gemini API with a key from Google AI Studio
Best for
Fast routing, tool selection, safety checks, and grading steps inside an app or agent.
When to use it
When a step only needs a decision, such as which tool to call or whether an answer passes a rubric, and a full text response would be slower and cost more.
Who benefits
Developers building agents and review pipelines on the Gemini API.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →
