LATEST

← Back to GPN · All articles

Google Launches Gemini Decisions API, Powered by New Gemini Decision 1 Model

Google Launches Gemini Decisions API, Powered by New Gemini Decision 1 Model

OFFICIAL Written by GPN · Nov 11, 2026, 6:50 PM ET · · AI

Google has introduced the Gemini Decisions API, a new endpoint for fast, closed-set decisions, powered by a new model called Gemini Decision 1. It is available now through 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, returning probabilities and confidence scores. A single request can carry one multimodal input — text, images, audio, video, or PDFs up to 256K tokens — together with up to 1,000 independent questions, and the API returns answers in 150 to 250 milliseconds end to end, with median model compute of 50 to 100 milliseconds.

The API supports three decision types in one pass. Yes/no checks estimate the probability that a condition holds, with optional criteria for what counts as true or false. Multiple-choice questions select from 2 to 255 options and return the winner with normalized probabilities for every candidate. Rubric scoring grades an input across an ordered scale, returning a continuous weighted score and per-level probabilities. Every answer carries a confidence score from 0 to 1, so code can route ambiguous cases to a fallback or a human reviewer.

Google says Gemini Decision 1 leads across a suite of benchmarks covering agent routing, reasoning, ranking, and multimodal understanding, with the lowest calibration error, and that it is nearly five times cheaper across the shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API. Pricing is $0.10 per 1 million input tokens, with no output tokens billed, no variable thinking-token bills, and no separate transcription or OCR costs.

Teams inside Google are already using it as a low-latency control plane. Gemini Notebook uses it as a real-time router to direct queries to the best model tier, cutting latency for everyday queries by up to 40 percent. Stitch uses it to generate playable wireframes of a product flow in seconds and apply edits by voice or tap. CC from Google Labs uses it to pick emoji reactions from a palette of more than 200 options, and Google Search uses it as a safety layer to detect adversarial behaviour against MCP tools.

The API is available now, with a no-cost tier in Google AI Studio for prototyping, plus demo apps and Python, JavaScript, and REST guides. Ecosystem integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit, and OpenCode, alongside the google-genai SDKs, with support in Gemini in Google Cloud coming soon.

Facts gathered from

More on this