Google launches Gemini Decisions API with multimodal model
google introduces gemini decisions api, powered by gemini decision 1 model, for fast, calibrated multimodal decisions across text, images, audio, video, and pdfs.
google has launched the gemini decisions api, which is powered by the new gemini decision 1 model. this api allows users to make fast, probabilistic choices across text, images, audio, video, and pdfs. it can handle up to 1,000 yes/no, choice, and rubric-scoring questions in a single pass, providing confidence scores for multiple questions. the api is designed to be cost-effective, with a latency of 150-250 ms end-to-end and a cost of $0.10 per 1m input tokens. the gemini decision 1 model leads across benchmarks, with the lowest calibration error, and is nearly 5x cheaper than gemini 3.5 flash-lite with the interactions api.