Google launched the Gemini Decisions API on Gemini Decision 1, a model that scores options instead of writing text

Google announced the Gemini Decisions API on 2026-11-11, a new endpoint for fast, closed-set decisions that runs on a dedicated model, Gemini Decision 1 (gemini-decision-1). Instead of generating answer text token by token, the model scores the candidate options in a single forward pass and returns probabilities and a confidence score between 0 and 1. Google pitches it for bounded choices inside agent systems: tool selection, policy checks, model routing and grading context.

A request carries one shared input of up to 256K tokens and up to 1,000 independent questions. Three question types are supported: yes/no, multiple choice with 2 to 255 options, and scoring against an ordered rubric. The model takes text, images, audio, video and PDFs natively. Google quotes 150-250 ms end-to-end latency, with a median of 50-100 ms of model compute, and says latency stays nearly flat from 1 to 100 questions per request.

Pricing is 0.10 dollars per million input tokens and nothing for output tokens, with the shared input billed once per request however many questions it carries. Google claims the Decisions API is nearly 5x cheaper across its benchmark suite than Gemini 3.5 Flash-Lite through the Interactions API. It is available through the Gemini API and Google AI Studio, with a free tier for prototyping and Google Cloud support “coming soon.”

Why it matters: Google is the third major vendor in about five weeks to ship a separate decision-model API, after Microsoft Decision 1 and OpenAI’s Decisions API, turning “classify, route, pick” into its own product category priced on input alone.

What it does not show: Google says the model “leads across the suite, with the lowest calibration error” but publishes no numeric benchmark scores in the announcement, so the accuracy and calibration claims cannot be checked from the post.