Google releases the Gemini Decisions API for closed choices

Google has released the Gemini Decisions API, a new endpoint for closed choices such as yes-or-no checks, multiple choice, and rubric scores. It says the API is available now in Google AI Studio, on a new model called Gemini Decision 1.

The API scores options instead of writing an answer. Google says a developer can send one input, including text, images, audio, video, or a PDF, of up to 256,000 tokens, plus as many as 1,000 questions. It says the model returns a probability and a confidence score from 0 to 1 in one pass, rather than generating text token by token. Google says end-to-end latency is 150 to 250 milliseconds.

Google says the API costs $0.10 per million input tokens and does not bill output tokens. The shared input is billed once, no matter how many questions are attached. A no-cost tier is available in Google AI Studio for prototyping. Google says the API is nearly five times cheaper than Gemini 3.5 Flash-Lite with the Interactions API on the company's shared benchmark set. It says support in Gemini on Google Cloud is coming soon, and that the model is already listed on OpenRouter and in several developer tools.

Three question types share one request. Google says a yes-or-no check estimates whether a condition holds. A choice question picks from 2 to 255 options and returns a probability for each. A score question grades an input on an ordered rubric that starts at 0. Google says Gemini Notebook already uses the API to route queries, and that everyday queries there are served with up to 40 percent lower latency. The post is dated November 11, 2026.