OpenAI's Decisions API is now generally available

OpenAI says its Decisions API, which entered public beta on October 6, is now generally available. According to OpenAI, apps and agents can use it to classify text and images, evaluate inputs and decide what happens next without generating a full model response. In the beta announcement, OpenAI said it makes decisions up to 10x faster than GPT-6 Luna through the Responses API.

Since the beta, OpenAI says it has added:

• Native GPT-Live integration, so voice apps can react as people speak.
• Prompt caching, to lower costs when reusing context.
• Native JSON inputs, for passing structured app data directly.
• Images in individual question instructions, to compare multiple images against a shared reference.
• Up to 400 questions per request, twice the previous limit.
• Inference residency in the US and EU, and added capacity in several regions in Asia.

How it works and what it costs: developers define a question and its allowed answers, supply text, images or JSON, and get back one of three answer types: a probability (predicate), a choice, or a score. OpenAI says it is built with GPT-6 Luna and available through a dedicated Decisions endpoint. It lists input at $0.10 per million tokens, cached input at $0.01 per million, and no output-token charge.

OpenAI quotes customer results, which are their own figures: Box saw about 5x faster route selection on 30 test cases with the same accuracy as the Responses API; Datadog reports 40x faster p95 than frontier models with comparable accuracy; Ramp reports 4x faster and 30% cheaper than GPT-6 Luna; Sierra reports under 280 ms p95 and 90% lower cost per call; Speak reports time to next action falling from 1.4 s to 0.13 s with GPT-Live.