Sakhanda Wire
NVDA $154.00 -1.37% MSFT $506.28 -2.26% GOOGL $280.87 -1.00% META $620.34 -0.97% AMZN $256.88 -0.34%
← Back to the news

Google introduces Gemini Decision 1 for large-scale closed-ended decisions

Google DeepMind has introduced the Gemini Decisions API, designed to handle fast, closed-ended tasks such as yes-or-no questions, multiple-choice selections and ratings on a scale. Its Gemini Decision 1 model can process up to 1,000 independent questions in one pass using text, images, audio, video or PDFs.

The system directly scores the available options and returns probabilities and confidence values in 150 to 250 milliseconds. Google says it uses the API internally for model routing in Gemini Notebook, design prototyping in Stitch and safety checks in Google Search. In one example, a kitchen-counter image was assessed for stains, a suitable cleaning action and severity, producing confidence of 0.95, a 98 percent result and a score of 1.19 out of 2.

Google lists pricing at $0.10 per million input tokens, with no charge for output tokens. The company says this is about five times cheaper than Gemini 3.5 Flash-Lite. The API is available through Google AI Studio, while integrations with OpenRouter, LangChain, Vercel and other platforms are being introduced. Google also says the model leads its benchmark suite in several categories and has the lowest Top-1 ECE calibration error.

Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.

Originally published by The Decoder on

Read the original on The Decoder ↗

The reporting and the image belong to The Decoder and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news