November 16, 2026

Google Launches Gemini Decision 1 for Fast Bulk Scoring

Google DeepMind has released a specialized API that scores up to 1,000 closed-ended questions in a single pass within milliseconds.

Google DeepMind has introduced the Gemini Decisions API, a new interface designed for fast, closed-ended decisions such as yes/no questions, multiple choice selections, and scale-based ratings, according to a report from the-decoder.com.

The underlying model, Gemini Decision 1, can process up to 1,000 independent questions in a single pass across text, images, audio, video, and PDF inputs. It scores options directly and returns probabilities along with confidence values in 150 to 250 milliseconds, the outlet reported.

Google said it already relies on the API internally for several tasks, including dynamic model routing in Gemini Notebook, design prototyping in its Stitch tool, and safety checks within Google Search.

Pricing is set at $0.10 per million input tokens with no charge for output tokens, which Google says makes it roughly five times cheaper than Gemini 3.5 Flash-Lite. The API is available now through Google AI Studio, with integrations for OpenRouter, LangChain, Vercel, and other platforms said to be rolling out.

The-decoder.com noted that Gemini Decision 1 arrives amid a broader wave of similar specialized decision models. The startup Jev introduced a comparable offering in recent weeks, and OpenAI, Cloudflare, and Microsoft have since released their own versions, suggesting a growing market segment focused on lightweight, high-throughput scoring tasks rather than open-ended generation.

By separating fast, structured decision-making from general-purpose language generation, these specialized models aim to cut costs and latency for applications that need rapid classification or rating at scale, such as content moderation, routing, and automated evaluation pipelines.

Based on reporting by the-decoder.com.

Leave a Reply

Your email address will not be published. Required fields are marked *