Google Launches Gemini Decisions API, Charging $0.10 per Million Input Tokens
2 day ago / Read about 0 minute
Author:小编   

Google has launched the Gemini Decisions API, an endpoint powered by the Gemini Decision 1 model that helps AI agents make predefined decisions quickly without generating lengthy text responses. The interface enables developers to evaluate up to 1,000 independent questions against shared multimodal inputs such as text, images, audio, video, and PDFs. Rather than generating responses token by token, Gemini Decision 1 scores predefined options in a single forward pass, returning probabilities and confidence scores with end-to-end latency of 150–250 milliseconds. According to Google, developers can submit yes/no checks, multiple-choice questions with up to 255 options, or scoring requests based on predefined rubrics—all in a single API call.