Google launches the Gemini Decisions API and Gemini Decision 1

Google has introduced the Gemini Decisions API, a Gemini API endpoint for fast, closed-set decisions, powered by a new model, Gemini Decision 1 (gemini-decision-1). It is available through the Gemini API in Google AI Studio.

A request takes one multimodal input (text, images, audio, video and PDFs, up to 256K tokens) and up to 1,000 independent questions. The questions can be yes/no checks, multiple choice (2 to 255 options) or ordered rubric scores, and each answer comes with a confidence score from 0 to 1. Google says the model scores the options in a single forward pass instead of generating text, with 150-250 ms end-to-end latency (50-100 ms of model compute).

Google prices it at $0.10 per 1M input tokens, with no output tokens billed and a no-cost API tier for prototyping. It says it is nearly 5x cheaper across a shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API, and that it leads that suite with the lowest calibration error; these are Google's own claims.

Google says it already uses the API inside Gemini Notebook (as a model router, with up to 40% lower latency), Stitch, CC from Google Labs and Google Search. Integrations are rolling out in OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, with Gemini in Google Cloud support coming soon.