Gemini Decisions API

Google has introduced the Gemini Decisions API, powered by the new Gemini Decision 1 model, which can evaluate up to 1,000 yes/no, choice, and rubric-scoring questions in a single pass across multiple media types (text, images, audio, video, and PDFs) with 150-250ms latency. The API provides confidence scores and probabilities for bounded decisions like tool selection and policy checks at $0.10 per 1M input tokens with no output token charges, making it approximately 5x cheaper than comparable alternatives. Developers can start building immediately through Google AI Studio with access to documentation for Python, JavaScript, and REST.