Google launches Gemini Decisions API for structured queries

Google launched the Gemini Decisions API on November 11, 2026, powered by a new model called Gemini Decision 1. Unlike traditional large language models, it handles only three question types: yes-no, multiple choice, and scale-based ratings. It outputs concise answers with a confidence score and supports inputs up to 256,000 tokens across text, audio, images, and video. Google says it is nearly five times cheaper than its entry-level Gemini 3.5 Flash-Lite. The model outperformed rivals on seven of nine benchmarks tested, though competitor Jev was slightly more cost-efficient. Pricing is 10 cents per million input tokens.