Google launches Gemini Decision 1 for batch closed-ended scoring
Original title: Google joins the decision-model wave with Gemini Decision 1, scoring 1,000 questions in a single pass
The Decisions API scores up to 1,000 questions in one pass and returns probabilities in 150 to 250 milliseconds.
Google DeepMind introduced the Gemini Decisions API and underlying Gemini Decision 1 model for yes/no questions, multiple choice, and scale ratings. It handles text, images, audio, video, and PDFs, scoring options and returning probabilities with confidence values. Google says it already uses the API for Gemini Notebook routing, Stitch prototyping, and Google Search safety checks. It costs $0.10 per million input tokens with no output-token charge and is available in Google AI Studio.
Unconfirmed: Benchmark leadership and the cost comparison are Google's own claims.
- Google says pricing is about five times cheaper than Gemini 3.5 Flash-Lite.
- OpenRouter, LangChain, and Vercel integrations are still rolling out.
- Google claims the lowest calibration error, measured as Top-1 ECE.
- OpenAI, Cloudflare, and Microsoft recently shipped similar decision models.
- Vendors
- Organizations
- Google DeepMindOpenAICloudflareMicrosoft
From the original article
1 min read at the-decoder.com
Google Deepmind's new Gemini Decisions API evaluates up to 1,000 closed-ended questions in a single pass across text, images, audio, and video. Gemini Decision 1 returns results in 150 to 250 milliseconds at roughly five times lower cost than Gemini 3. 5 Flash-Lite, according to Google.
By Matthias Bastian · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.