Google launches Gemini Decision 1 for scoring up to 1,000 choices in one pass

Google's post dated 11 November 2026 introduces the Gemini Decisions API and a model it calls Gemini Decision 1, with the id gemini-decision-1, in the Gemini API in Google AI Studio. It says one request can carry a multimodal input, across text, images, audio, video and PDFs, of up to 256K tokens, together with up to 1,000 independent questions. It says the model scores the options in one pass and returns probabilities and confidence scores, with end-to-end latency of 150-250 ms. The price on the post is $0.10 per 1M input tokens, with zero output tokens billed. It says there is an API no-cost tier in Google AI Studio for prototyping. It says support is coming soon to Gemini in Google Cloud. The post does not say the weights are released.

The post says the shared input is billed once per request, and that each question adds only its own instruction and criteria tokens. It describes three question types: a yes/no check, a multiple choice of 2 to 255 options, and an ordered rubric score. It says that, with zero output tokens billed, Gemini Decision 1 was nearly 5 times cheaper across a shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API. That comparison is Google's.

What it means for business: the priced API call on the post is $0.10 per million input tokens and $0 for output tokens, for closed-set choices rather than generated text. The post does not release weights. This describes the announcement. It is not advice on using the scores in a decision that affects a person.