AdvertiseWatchSubscribe
Last scan 55 h agoMonday, November 16, 2026

553 points60 comments

Google launches Gemini Decisions API for 1,000-question multimodal scoring

Gemini Decisions API: preview

What is Gemini Decisions API?

The Gemini Decisions API lets you submit up to 1,000 yes/no, multiple-choice or rubric questions together with text, images, audio, video or PDF content, and returns probability scores for each option in a single pass. It delivers results in about 150-250 ms and costs $0.10 per million input tokens.

Who it is for

Developers who need fast, calibrated decisions for routing, policy checks, or grading can use it to replace slower text-generation approaches.

The morning email · free

Get tomorrow's biggest AI launches before everyone else.

One short email each morning: what launched, why it matters, how to try it. Five minutes, no spam, unsubscribe any time.

The story so far

Early Signal first spotted Gemini Decisions API on November 11, 2026, with 553 points. On its busiest day it gained 367 points.

Questions about Gemini Decisions API

What do I need to run Gemini Decisions API?
Google AI Studio API key and a HTTP client (e.g., curl or a language SDK).

Get the signal first.

Join the list for the morning email: the day's biggest AI launches, explained in five minutes. Unsubscribe any time.

Prefer a reader? Follow the RSS feed.