Google launches Gemini Decisions API that scores 1,000 choices without generating text
Google's new Gemini Decision 1 model scores up to 1,000 yes/no, choice, and rubric questions in one pass for $0.10 per 1M input tokens.
By Ryan Merket · Published
Primary source: x.com
Why it matters
Agent systems burn money and latency on generative calls that only need to return a branch, a rank, or a score. By pricing decisions at $0.10 per 1M input tokens with no output charge and returning calibrated confidence scores, Google is trying to own the routing and policy layer that sits in front of larger models - a high-volume position that compounds across every call an application makes.
Google's new Gemini Decision 1 model scores up to 1,000 yes/no, choice, and rubric questions in one pass for $0.10 per 1M input tokens.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.