Google launches Gemini Decisions API
Google announced the Gemini Decisions API, a developer endpoint powered by Gemini Decision 1 for closed-set decisions across text, images, audio, video, and PDFs. It can score up to 1,000 yes/no, multiple-choice, and rubric questions in one request, returning probabilities and confidence scores; developers can access it through Google AI Studio. Google says the model delivers 150–250 ms end-to-end latency at $0.10 per million input tokens with no output-token charges, while its benchmark, calibration, and cost comparisons remain vendor claims. Why it matters: The API provides purpose-built primitives for routing, policy checks, grading, and tool selection. Google reports uses in Stitch, Google Labs CC, and Google Search. What do you think?
Open the headline: source, AI briefing and more →Comments
…