Google Releases Gemini Decisions API and Gemini Decision 1 Model
Google has released the Gemini Decisions API, powered by the new Gemini Decision 1 model, now available on GoogleAIStudio. The model does not perform token-by-token text generation; instead, it scores closed-set choices for up to 1,000 questions, and can process text, images, audio, video, and PDFs in a single pass. It supports three decision types: yes/no, multiple-choice with up to 255 options, and rating scales. Input pricing is $0.10/1M tokens, output tokens are not billed, it is about 5 times cheaper than Flash-Lite, and it leads on multiple benchmarks with the lowest calibration error.
Why read this
SelectedAI score 71
The new model replaces generative output with closed-set scoring; together with pricing and benchmark performance, it helps determine the applicable boundaries of such decision interfaces.
Topics
Body
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring - $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite) - leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)