Gemini Decision 1 is Free on Google AI Studio
What happened
Google AI Studio now hosts the Gemini Decision 1 API, which lets developers ask typed questions—yes/no, choice, or score—about shared input data and receive calibrated probabilities without generating any text tokens. Each request can include multiple isolated questions that run in a single forward pass, keeping latency flat. The API returns a probability for yes/no questions, the top option plus probabilities for choice questions, and a weighted average score with a legend for score questions. It requires SDK version 3.2 or later and works by sending a model, shared input, and a map of questions. The response also includes a confidence value to guide automatic or escalated actions.
Why it matters
This lets code make faster, more reliable decisions without parsing text, which can simplify automation and reduce errors for developers building AI‑driven workflows.
Reality check
An automated, sceptical read of the sourceIncremental. The feature extends existing Gemini models with structured decision outputs, improving usability but not introducing a fundamentally new capability.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Google
Google Search gets a major upgrade with Gemini 4 HydrogenGoogle · 12 Nov 2026Introducing Gemini 4 HydrogenGoogle · 12 Nov 2026Gemini 4 HydrogenGoogle · 12 Nov 2026Gemini Decisions API: Fast, calibrated multimodal decisionsGoogle · 11 Nov 2026Try Tabletop: Customizable, collaborative spaces for groups to plan, play and do more together.Google · 11 Nov 2026This page was collected from aistudio.google.com and summarised automatically by AIPulsee's pipeline. See how it runs.