Google introduces Gemini Decisions API that scores 1,000 closed-set choices in a single pass

📅 November 11, 2026 • Google blog — Google introduced the Gemini Decisions API, a new endpoint for fast closed-set decisions, powered by a new model, Gemini Decision 1 (gemini-decision-1), via the Gemini API in Google AI Studio. Instead of generating answer text token by token, Gemini Decision 1 scores candidate options in a single forward pass and returns probabilities plus confidence scores. One request carries a shared multimodal input across text, images, audio, video and PDFs of up to 256K tokens, with up to 1,000 independent questions evaluated against it. Three question types, one confidence score Questions come in three types: a yes/no probability called noul, multiple choice with 2 to 255 options returning normalized probabilities for every candidate, and ordered rubric scoring returning a continuous weighted score with per-level probabilities. Every answer includes a confidence score from 0 to 1, so code can route ambiguous cases to a fallback or a human reviewer. Purpose-built use cases named by Google are tool selection, policy checks, model routing and context grading. The confidence score lets code gate on certainty. Latency and pricing Google reports end-to-end latency of 150–250 ms, median model compute of 50–100 ms contexts up to 16K tokens, with latency nearly flat from 1 to 100 questions per request. Pricing: USD 0.10 per 1M input tokens with zero output tokens billed. Per Google, this makes it nearly 5x cheaper across a shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API. A no-cost tier exists in Google AI Studio. Per Google, it leads benchmarks in routing, reasoning, ranking and multimodal understanding with the lowest calibration error. Where Google runs it and what changes Per Google, internal uses include dynamic model routing in Gemini Notebook with up to 40 percent lower latency for daily queries, wireframing in Stitch, emoji selection in CC from more than 200 options, and a safety layer for MCP tools in Google Search. Integrations are rolling out with OpenRouter, LangChain, Vercel AI SDK, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode alongside the google-genai SDKs. IMPACT — for agent builders: one-pass scoring changes the cost of routing, ranking and policy checks inside agent stacks. Scores arrive in one response. Sources: blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api x.com/sundarpichai/status/2120581155078729728 mezha.net/eng/news/mezha-c06fca3b9549fb95708df0f2_google_introduces_gemini Continue the conversation: https://t.me/AIAutomationArchitecture · Bluesky