Google has unveiled the Gemini Decisions API, a cutting-edge artificial intelligence tool aimed at helping businesses and developers streamline decision-making processes. Built on the Gemini Decision 1 model, this API allows users to evaluate up to 1,000 questions related to text, images, audio, video, and PDF documents in a single request, offering a more efficient and cost-effective solution.
The Gemini Decisions API distinguishes itself from traditional AI models by assessing multiple options simultaneously rather than step by step. This approach yields probability estimates and confidence scores, enhancing decision-making tasks such as tool selection, policy checking, query routing, and information analysis. Google reports that the API achieves response times between 150 and 250 milliseconds, with pricing set at $0.10 per million input tokens. Notably, no charges are applied for output tokens, and shared input is billed only once, irrespective of the number of questions evaluated.
Designed to support yes-or-no decisions, multiple-choice selections, and ranking options based on specified criteria, the API boasts multimodal capabilities that enable it to process up to 256,000 tokens of combined input. This makes it particularly suitable for complex business applications requiring detailed evaluations.
Google has already integrated this technology into several of its products, including Gemini Notebook, Stitch, and Google Search, to enhance query routing, product design, and content safety. The introduction of the Gemini Decisions API marks an expansion of Google’s AI ecosystem, offering developers and businesses a more rapid and affordable solution for automated decision-making tasks.