# Google releases Gemini API for scoring bounded decisions

_Published Wednesday, November 11, 2026 at 1:22 PM EST · AI · Latest · Tier 2 — Notable_

![Google releases Gemini API for scoring bounded decisions — Primary](https://storage.googleapis.com/gweb-uniblog-publish-prod/images/gemini__decisions__blog-header_2784x1566.width-1300.png)

Google introduced the Gemini Decisions API in Google AI Studio, giving developers access to Gemini Decision 1 for tasks such as selecting tools, routing requests and checking policies. The model scores predefined options in a single pass rather than generating answers token by token.

The endpoint accepts text, images, audio, video and PDFs, with inputs up to 256K tokens and up to 1,000 independent questions. Google charges $0.10 per 1M input tokens and no output-token fees. Each answer includes confidence scores that software can use to send uncertain cases to another model or a human reviewer. Google's stated 150-250 ms end-to-end latency applies to contexts up to 16K tokens.

## Sources

- [AI](https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/)

---
Canonical: https://techandbusiness.org/newswire/nc9-2-_tpXzpDuUhvV1bSC
Published: 2026-11-11T18:22:23.435Z
Story chronology: 2026-11-11T18:00:00.000Z
Retrieved: 2026-11-12T01:04:03.580Z
Publisher: Tech & Business (techandbusiness.org)