Google introduced the Gemini Decisions API, a new endpoint for closed-set decisions powered by a new model, Gemini Decision 1, available through the Gemini API in Google AI Studio. A single request can pair one input of up to 256K tokens, across text, images, audio, video and PDFs, with up to 1,000 independent questions. Supported question types are yes/no, multiple choice with 2 to 255 options and ordered rubric scores, and each answer comes with a confidence score from 0 to 1 so code can send ambiguous cases to a fallback or a human reviewer.
Rather than generating text, the model scores candidate options in a single pass. Google says end-to-end latency is 150 to 250 ms and stays nearly flat from 1 to 100 questions per request. Pricing is $0.10 per 1M input tokens with no output-token charges, and the shared input is billed once per request. Google says the model leads its benchmark suite with the lowest calibration error and is nearly 5x cheaper on that suite than Gemini 3.5 Flash-Lite with the Interactions API.
Google says teams including Gemini Notebook, Stitch and Search already use the API; Notebook uses it to route queries and serves everyday ones with up to 40% lower latency. Integrations are rolling out across tools such as OpenRouter, LangChain and Vercel, and support in Gemini in Google Cloud is coming soon.