Google launches the Gemini Decisions API (Gemini Decision 1 model)
Google launches the Gemini Decisions API, built on the Gemini Decision 1 model (via the Gemini API in AI Studio): it evaluates up to 1,000 yes/no, choice or scoring questions in one pass over a multimodal input (text, image, audio, video, PDF), with probabilities, confidence scores and ~150-250 ms latency.
What the article says
On 11 November 2026, Google launched the Gemini Decisions API, an endpoint built on its new Gemini Decision 1 model, available through the Gemini API in Google AI Studio. It targets closed-set decisions: tool selection, policy checks, model routing and scoring.
In a single pass it evaluates up to 1,000 questions (yes/no, multiple choice, rubric scoring) over one multimodal input (text, image, audio, video, PDF), returning probabilities and a confidence score, with about 150-250 ms latency and pricing of $0.10 per million input tokens and no billed output tokens.
Read the official article AnnuIA profile
Summary written by AnnuIA in its own words from the official page of Google (IA). The content and rights belong to the publisher: please read the original article.