Google on Wednesday introduced the Gemini Decisions API, a new endpoint for fast, closed-set decisions powered by a model it calls Gemini Decision 1 (gemini-decision-1), available through the Gemini API in Google AI Studio, the company said in an official blog post.
Developers can pass one multimodal input — text, images, audio, video and PDFs, up to 256K tokens — along with up to 1,000 independent questions. Rather than generating answer text token by token, Gemini Decision 1 scores candidate options in a single forward pass and returns probabilities and confidence scores in 150-250 milliseconds end-to-end, at $0.10 per 1 million input tokens with zero output tokens billed, Google said. Median model compute is 50-100 milliseconds and stays nearly flat from 1 to 100 questions per request at contexts up to 16K tokens, the company said. Google said the Decisions API is nearly five times cheaper across a shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API; those latency, price and benchmark claims are the company’s.
The API supports three question types in one request: noul, a yes/no probability with optional true/false criteria; choice, which selects among 2 to 255 options and returns normalized probabilities; and score, an ordered rubric starting at 0 with a continuous weighted score. Every answer includes a confidence score from 0 to 1 so software can send ambiguous cases to a fallback or a human reviewer, Google said. The company described intended uses such as tool selection, policy checks, model routing and context grading, and said image and video resolution can be tuned to control visual detail and token cost.