Google launches Gemini Decisions API for faster, cheaper AI decision-making

Google has released the Gemini Decisions API, powered by the Gemini Decision 1 model, designed for AI tasks requiring rapid data evaluation, option selection, and condition checking. The model processes up to 1,000 questions in a single request with a median computation time of 50-100 milliseconds. Unlike standard generative models, Gemini Decision 1 evaluates provided options in a single pass rather than sequentially generating text. It supports text, images, audio, video, and PDFs within a 256,000-token context, offering three evaluation modes: truth probability, best-option selection, and scale-based scoring, each returning a confidence score from 0 to 1. Google positions the API as a cost-efficient intermediary control layer, claiming it is nearly five times more economical than Gemini 3.5 Flash-Lite under identical conditions. Pricing is $0.10 per million input tokens with no output token charges, and developers can access a free tier via Google AI Studio.