OpenAI Previews Decisions API for Faster Model Choices

Oct 1, 2026
The limited preview lets OpenAI's Luna model choose among predefined options, offering a faster approach for classification and agent monitoring.
OpenAI Previews Decisions API for Faster Model Choices

OpenAI previewed its Decisions API at Dev Day, according to TechCrunch. CEO Sam Altman said the API lets the Luna model choose among predefined options, such as image categories or possible agent actions.

The limited preview appears similar to TypeSafe AI's Jev model, which returns probabilities for a fixed set of choices. This structure can make classification and software automation faster and cheaper than using a large language model to generate text, although the two products have not yet been compared publicly.

One possible use is monitoring AI agents. QueryStory built a demonstration that checks each agent action against its assigned task, blocks actions judged harmful, flags uncertain actions for review and permits the rest. The demonstration cost $2.94 to run with Jev, compared with $372 using a frontier model.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.