Google has launched the Gemini Decisions API, a new endpoint for fast, closed-set decisions such as tool selection, policy checks, model routing and grading context. It runs on a new model, Gemini Decision 1 (gemini-decision-1), and was announced on November 11.
Instead of generating text, the API scores a fixed set of candidate answers. It returns probabilities and confidence scores, which code can use to send unclear cases to a fallback model or a human reviewer. One request takes a single multimodal input of up to 256K tokens (text, images, audio, video or PDFs) and can evaluate up to 1,000 independent questions about it in one pass. Supported question types are yes/no checks, multiple choice with 2 to 255 options, and ordered rubric scores.
Google reports end-to-end latency of 150 to 250 milliseconds, of which 50 to 100 milliseconds is model compute. It says latency stays nearly flat between 1 and 100 questions per request. Pricing is $0.10 per million input tokens, and output tokens are free. The shared input is billed once per request no matter how many questions are asked. Google says the API is nearly 5x cheaper than using Gemini 3.5 Flash-Lite with the Interactions API across its benchmark suite, and that it had the lowest calibration error in that suite.
The API is available now through the Gemini API and Google AI Studio, which has a free tier for prototyping. Google says integrations are rolling out with OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, and that support in Google Cloud is "coming soon." Google also says its Gemini Notebook product saw up to 40% lower latency on everyday queries after using the API for model routing.
For teams running agent pipelines, this is a dedicated, cheap option for the classification steps that sit between expensive model calls, such as picking a tool, checking a policy or choosing which model to use. Those steps currently often run on general-purpose chat models.