01 What happened
Google has introduced the Gemini Decisions API, a new endpoint designed for rapid, calibrated decision-making across text, images, audio, video, and PDFs.
02 Key details
- Powered by Gemini Decision 1, the API processes up to 1,000 independent questions in a single forward pass.
- Supports three decision types: noul (yes/no), choice (2–255 options), and score (rubric-based grading) with confidence scores.
- Features end-to-end latency of 150–250 ms and is priced at $0.10 per 1M input tokens with no output token charges.
- Available via Google AI Studio's no-cost tier, with integrations for LangChain, Vercel, and more.
03 Why it matters
It provides a low-latency, cost-effective alternative to token-by-token generation for tasks like model routing and policy enforcement.
04 Who it matters to
AI developers, machine learning engineers, AI agent developers and software developers.
Original source