AIToday
AI Business & IndustryGIGAZINE AIPublished: Oct 7, 2026, 19:01 JST

OpenAI opens Decisions API beta, up to 10x faster than GPT-6 Luna

OpenAI opens Decisions API beta, up to 10x faster than GPT-6 Luna

3 Key Points

  1. What happened

    OpenAI released the Decisions API in public beta, saying it makes decisions up to 10x faster than GPT-6 Luna through the Responses API. It is called via a dedicated "POST /v1/decisions" endpoint and runs only on GPT-6 Luna.

  2. Why it matters

    It returns compact results such as probabilities, chosen options, and confidence scores, so teams routing large volumes of inquiries or picking an AI agent's next tool can get decisions in near real-time rather than generating full written answers.

  3. What to watch

    OpenAI says it plans general availability within a few weeks, and recommends tuning thresholds with labeled data from real apps. Watch whether teams treat low-confidence results as a trigger to send cases for human review.

WHO IT HITSThis lands on developers and support or operations teams that need to route high volumes of inquiries or pick an AI agent's next tool, since the API narrows the job to just returning a decision.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

The Decisions API is aimed at a narrower job than a general generation API. Ordinary generation APIs carry broad capabilities, including writing full answer text, but tasks like classifying large volumes of inquiries or choosing an AI agent's next tool hinge on the speed of the decision itself. By limiting its purpose to decision-making, the new API is designed to return results quickly.

OpenAI has also built in safeguards against treating its output as final. The company recommends adjusting thresholds using labeled data collected from real applications, weighing the impact of handling something incorrectly against missing something that should have been handled. It also returns a confidence level, so an operation such as sending low-confidence cases to a human can be set up.

How much of this lands may depend on whether developers take OpenAI's advice on threshold tuning, and on general availability arriving within the few weeks the company has indicated. For teams already running high-volume inquiry routing, the appeal is likely to rest on cost and latency rather than raw capability.

FAQ
What kinds of questions can the Decisions API answer?
It supports three formats: predicate, which returns the probability that a condition holds; choice, which picks the best fit from options the developer supplies; and score, which rates input against a set scale.
Does the Decisions API work with images?
Yes. Images can be used as input alongside text. In one example, a product photo asked whether a dent was present and the API returned a 0.86 probability, letting developers set a rule such as sending anything at 0.8 or above to human review.
Which model does the Decisions API use?
At the time of writing, the only model available is GPT-6 Luna, the fast, low-cost model from the GPT-6 series that arrived in September 2026.

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleOpenAI posts new math results from internal model in GitHub repository