Gemini Decisions API scores up to 1,000 multimodal decisions in one pass
Google’s new API, powered by Gemini Decision 1, returns probabilities and confidence scores for closed-set decisions across text, images, audio, video, and PDFs.
AT A GLANCE
Key points
- Up to 1,000 independent decisions per input
- Text, image, audio, video, and PDF support
- Closed-set answers with probabilities and confidence
What is changing?
Google made the Gemini Decisions API available on November 11 through the Gemini API in Google AI Studio. Powered by Gemini Decision 1, the endpoint evaluates up to 1,000 independent yes/no, multiple-choice, or rubric-scoring questions in a single pass over one text, image, audio, video, or PDF input. Each answer includes a probability and confidence score.
Google lists support for inputs up to 256K tokens, end-to-end latency of 150–250 ms, and pricing of $0.10 per million input tokens with no output-token charge. The API is designed for bounded decisions such as tool selection, policy checks, model routing, and context grading rather than free-form explanations. The provider’s latency and cost claims should still be measured on real workloads.
Explore the original sources
Source date: 11 November 2026.
Published by AI Radar: 11 Nov 2026, 22:05 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…