All stories
OpenAI Decisions API Launches Developing

OpenAI previews Decisions API for fast, bounded model choices

At its September DevDay preview, OpenAI proposed fast, predefined model choices. Public beta followed on October 6; this report preserves the original announcement.

Newer coverageOpenAI opens Decisions API public beta for text and image classification

Sources (2)

Why now September 30 reporting adds detail to the Decisions API announced at OpenAI DevDay and puts it in the growing market for small, structured model decisions.

Storyline / Report 1 of 2

OpenAI Decisions API access

Latest report
Full timeline 2 reports
  1. Developing
    OpenAI previews Decisions API for fast, bounded model choices (current report)
  2. Source-backed
    OpenAI opens Decisions API public beta for text and image classification

October update: public beta is now available

OpenAI announced public beta access for all developers on October 6, after the preview covered below. Read the public-beta launch report for that development, or the Decisions API overview for documented pricing, access and examples. The original report was published September 30; its limited-preview details describe that earlier stage.

The task OpenAI is targeting

OpenAI previewed a Decisions API at DevDay on September 29, TechCrunch reports. CEO Sam Altman described giving the company’s Luna model a predefined set of choices rather than asking it for an unrestricted text answer. His examples included choosing categories for an image and selecting among agent behaviors. Altman said the narrower task is intended to produce fast responses while retaining capabilities such as image understanding, language support and safety protections. Those are product claims from the announcement, not independently measured results.

TechCrunch compares the approach with TypeSafe AI’s Jev, which also returns structured decisions for software workflows. The comparison describes a category of use, not proof that OpenAI copied Jev or that the two products perform alike. A bounded choice may be useful where software needs a category, score or action selection repeatedly, including inside an AI agent.

What has not been tested publicly

At the time of the September 30 report, the API was in limited preview, according to TechCrunch. The publication said it had not yet seen developers test it publicly. That left important questions about access, pricing, output calibration and real-world speed unanswered in that source. TechCrunch discusses agent monitoring as a possible application, but it does not report that Decisions API already powers OpenAI’s security systems or that it would have prevented any past incident.