Google Launches Gemini Decisions API for Multimodal Decisions

Google on November 11, 2026 introduced the Gemini Decisions API, a new endpoint powered by its Gemini Decision 1 model and available through the Gemini API in Google AI Studio. The API evaluates up to 1,000 independent questions across text, images, audio, video and PDFs in a single request, returning probabilities and confidence scores rather than generated text.

The endpoint is built for bounded judgments such as tool selection, policy checks, model routing, context grading and ranking, rather than prose or explanations. A request combines one shared input with independent questions; Gemini Decision 1 scores candidate options in a single forward pass instead of decoding an answer token by token, allowing programs to branch, sort and route directly on typed responses.

The Decisions API supports three question types in one pass: yes/no checks that estimate the probability a condition holds, multiple-choice questions with 2 to 255 options, and ordered rubric scores. Every answer includes a confidence score from 0 to 1, defined as the estimated probability that the top answer is correct. Google says questions cannot see one another, and adding or removing one does not change the other answers.

Google reports 50-100 milliseconds of median model-compute latency and 150-250 milliseconds of end-to-end latency across multimodal inputs and contexts up to 16K tokens, with latency staying nearly flat from one to 100 questions per request. The shared input can reach 256K tokens, and the context window covering the shared input and all questions is 262,144 tokens.

Pricing is $0.10 per 1 million input tokens, with zero output tokens billed. The shared input is billed once per request regardless of question count, while each question adds its own instruction and criteria tokens. Google describes Gemini Decision 1 with the Decisions API as nearly five times cheaper across the shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API. A no-cost AI Studio tier supports prototyping.

Google says Gemini Decision 1 led its benchmark suite spanning agent routing, reasoning, ranking and multimodal understanding, with the lowest calibration error. The company already uses the API internally: Gemini Notebook uses it as a real-time router for model tiers and thinking levels, delivering up to 40% lower latency for everyday queries, while Stitch's rapid canvas experiment uses it to generate playable wireframes and CC from Google Labs uses it to select among more than 200 emoji reactions.

Initial access is limited to the Gemini Developer API v1beta with Gemini Decision 1. Question instructions are text-only, and conversation history and tool-call blocks are unsupported. Context caching, the Batch API, and Flex or Priority inference are also unavailable. Ecosystem integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, with support for Gemini in Google Cloud listed as coming soon.

Alphabet (GOOGL) shares were up 2.1% in delayed trading.