Google has unveiled the Gemini Decisions API, a cutting-edge artificial intelligence tool aimed at streamlining decision-making processes for businesses and developers. The new API leverages the power of the Gemini Decision 1 model to process up to 1,000 queries in a single request, handling data from text, images, audio, video, and PDF documents.
Unlike conventional AI models that tackle each step sequentially, the Gemini Decisions API evaluates multiple options simultaneously, offering probability estimates and confidence scores. This allows for quicker decision-making in tasks such as tool selection, policy verification, query routing, and data analysis.
Google claims that the API delivers response times between 150 and 250 milliseconds. The pricing is set at $0.10 per million input tokens, with no charges for output tokens, and shared input is charged only once, regardless of the number of questions assessed. This cost-effective approach makes it an attractive option for businesses seeking efficient solutions.
The API supports various decision-making formats, including yes-or-no questions, multiple-choice selections, and rankings based on given criteria. Its robust multimodal capabilities enable the processing of up to 256,000 tokens of combined input, making it well-suited for complex business applications.
Google has already integrated this technology into several of its products, such as Gemini Notebook, Stitch, and Google Search, to enhance query routing, product design, and content safety. This launch bolsters Google’s AI ecosystem by providing developers and businesses with a faster and more affordable tool for executing individual evaluations and automated decision-making tasks.