Google Launches Gemini Decisions API for Multimodal AI Workflows

Google launched the Gemini Decisions API on November 11, 2026, enabling multimodal AI workflows that evaluate up to 1,000 independent questions per request across text, images, audio, video, and PDFs. The API uses Gemini Decision 1 model to score candidate options in a single forward pass, optimizing software control flow with confidence scores for each answer. It supports yes/no, fixed-choice, and rubric questions with low latency and is priced at $0.10 per million input tokens.