Google has introduced Gemini Decision 1 via a new Decisions API, which scores inputs directly without generating token-by-token text output. It handles text, images, audio, video and PDFs in a single pass, supports yes/no, multiple-choice and rubric-style questions with confidence scores, and keeps latency around 150-250 ms end-to-end regardless of input volume up to 100 questions per request.
blog.google
· 2026-11-11
OpenAI made its Decisions API generally available to all customers, adding voice and visual input options and reducing global latency through geographically targeted inference. The API repurposes ChatGPT Luna to deliver fast, low-cost classification-style decisions, cutting response times from seconds to under 200 milliseconds, according to OpenAI product lead Nikunj Handa. Early customers including Box, Datadog, Ramp and Speak have already used it to replace standard LLM calls in their workflows.
techcrunch.com
· 2026-10-22
OpenAI has released a public beta of a new Decisions API that evaluates text and images and returns typed answers—probabilities, choices, or scores—about 10x faster than its Responses API. The endpoint, POST /v1/decisions, currently supports only the gpt-6-luna model, and requests combine a model, shared input evidence, and a set of named questions. OpenAI says general availability is expected in the coming weeks.
developers.openai.com
· 2026-10-06
At OpenAI's Dev Day, CEO Sam Altman introduced a new 'Decisions API' that lets developers give the company's Luna model a predefined set of options to choose from, such as image categories or agent behaviors, returning fast, low-cost outputs. The tool appears similar to Jev, a classifier model released earlier this month by TypeSafe AI for software automation tasks. OpenAI's API is currently in limited preview, and TypeSafe did not respond to requests for comment on the similarities.
techcrunch.com
· 2026-09-30