On October 22, 2026, OpenAI made the Decisions API generally available. Built on GPT-6 Luna, it focuses on questions with bounded answers: how to classify an input, where to route a request, or which action an agent should take next.
Developers define a question and its allowed answers, then provide context as text, images or native JSON. The API returns one of three answer types, a probability that a condition is true, a choice from a fixed set, or a score against a rubric, which an application can use to decide what happens next.
OpenAI says the Decisions API makes these decisions up to 10x faster than calling GPT-6 Luna through the Responses API. Since the public beta it has added a native GPT-Live integration, prompt caching for reused context, inference residency in the US and EU, and up to 400 questions per request, twice the previous limit.
Early customers named by OpenAI include Box, Datadog, Ramp, Sierra and Speak, using it to classify and route documents, score the risk of agent commands before running them, attribute AI costs, and pick the next action in live conversations.
For people building websites and tools with AI, the many small calls inside a product, such as sorting form submissions, routing support messages or checking content, are good candidates for a dedicated decision endpoint that keeps the main experience fast.