AI Tools & Products
1h ago
Google Launches Gemini Decisions API for Multimodal Decision-Making
Nov 11, 2026
AI Summary
Google has introduced the Gemini Decisions API, which utilizes the Gemini Decision 1 model to facilitate rapid decision-making across various media types, including text, images, audio, video, and PDFs. The API allows users to evaluate up to 1,000 questions in a single pass, providing confidence scores and reducing costs significantly compared to previous models.
- The Gemini Decisions API is designed for fast, multimodal decision-making, processing inputs from text, images, audio, video, and PDFs.
- It can evaluate up to 1,000 yes/no, choice, and rubric-scoring questions in a single request, returning results with confidence scores.
- The API operates with low latency, typically between 150-250 milliseconds, and is priced at $0.10 per 1 million input tokens, with no charges for output tokens.
- Gemini Decision 1 model scores options in a single forward pass, avoiding token-by-token decoding, which enhances efficiency.
- The API is already being utilized by various teams within Google for rapid feature development without the need for custom classifiers.
- Ecosystem integrations are being developed with platforms such as OpenRouter, LangChain, and others, expanding the API's usability in different applications.
- Users can access the API through Google AI Studio, where they can obtain an API key and explore documentation for implementation.
geminiapimultimodaldecisionscalibrated