ToolOpenAI

OpenAI launches Decisions API for fast, low-cost decisions

Original title: Build more responsive apps with the Decisions API

Plain language

What it is: OpenAI has released the Decisions API, which is now generally available. It is designed to help applications and agents make fast, low-cost, and simple decisions.
How it works: The tool works by focusing on questions that have a limited set of answers. Users provide a question, the allowed answers, and context like text or images, and the system quickly returns a choice, a probability, or a score.
Where it is available: It is available through a dedicated endpoint. It can be used globally, with regional processing options in the US and EU, and additional capacity in Asia.
Example: Box uses the Decisions API to classify business documents and route them to the correct next step in their workflow.

What it is: OpenAI has launched the general availability of the Decisions API, built on the GPT-6 Luna model. It is optimized for low-latency, low-cost decision-making with bounded outputs, running up to 10 times faster than the Responses API.
How it works: Developers define a question, allowed answers, and context using text, images, or native JSON. The API supports up to 400 questions per request and returns one of three structured types: probability, choice, or score. It also features prompt caching and native GPT-Live integration.
Where it is available: The API is available via a dedicated Decisions endpoint. It supports regional processing in the US and EU, and integrates directly with GPT-Live sessions.
Example: Datadog uses the API to score the risk of agent-generated rshell commands before executing them to autonomously remediate issues.

The headline and explanation on this page are based on OpenAI's post. The full details are in the original.

Build more responsive apps with the Decisions API