Google has introduced the Gemini Decisions API, powered by its Gemini Decision model. The API is designed to help developers make faster and more cost-effective decisions by selecting from available options instead of generating lengthy text responses.

According to a blog post published by Google yesterday, the API can evaluate up to 1,000 independent questions in a single request. It supports text, images, audio, videos and PDF files.

The API supports three types of decisions: Yes or No assessments, multiple-choice selections and score-based evaluations. It can select from 2 to 255 options and provides probability and confidence scores to help identify uncertain results.

Google said the API can deliver response times of 150 to 250 milliseconds. It can be used for tasks such as selecting AI models, checking policies, choosing tools and evaluating information.

The company said Gemini Decision 1 is nearly five times cheaper than Gemini 3.5 Flash-Lite with the Interactions API across its shared benchmark tests. The service costs $0.10 per million input tokens, with no charges for output tokens.

Developers can access the API through Google AI Studio, with support from platforms such as OpenRouter, LangChain, Vercel and LiteLLM.