OpenAI Launches Decisions API for Faster App Responses

OpenAI has made the Decisions API generally available. The new interface is built with GPT-6 Luna and is designed to help applications make near real-time decisions. It claims to operate up to 10x faster than the Responses API. The system reduces inference time from one to three seconds down to 100, 120, or 180 milliseconds.

The API supports asking up to 400 questions per request. Developers can define a question, allowed answers, and context to distinguish them. The system supports three answer types: probability, choice, or score. It also allows images in question instructions. Prompt caching is supported for reused context. Regional processing is available in the US and EU.

Pricing for the Decisions API is set at $0.10 per million input tokens. Cached input costs $0.01 per million tokens. There are no output-token charges. OpenAI announced the tool at its developer day on September 29. The company used the API to improve the responsiveness of its Dots voice assistant. TypeSafe's Jev model created a category for deep learning models that act as super classifiers.