OpenAI's Decisions API is now generally available
Why it matters
OpenAI made its Decisions API generally available on Oct 22. It is built for the many small decisions inside apps and agents, like classifying an input, routing a request or picking the next action: you define a question and its allowed answers, and it returns a probability, a choice from your options, or a score against a rubric. It is built with GPT-6 Luna, and OpenAI says it is up to 10x faster than GPT-6 Luna through the Responses API. Pricing is $0.10 per 1M input tokens and $0.01 per 1M cached input tokens, with no output-token charges. New since the public beta: up to 400 questions per request (up from 200), prompt caching, native JSON inputs, images in question instructions, inference residency in the US and EU, and a native GPT-Live integration. Customer numbers quoted by OpenAI (self-reported by each company): Sierra runs under 280 ms p95, about 3x faster and 90% lower cost per call than its previous approach; Datadog reports 40x faster p95 than available frontier models with comparable accuracy for scoring agent-generated shell commands; Speak cut time to next action from 1.4s to 0.13s with GPT-Live. Caveat: gpt-6-luna is the only supported model for now.
Read the source: OpenAI (opens in a new tab)
All hits from 23 Oct 2026More AgentsGet the daily hits by email