Decisions API Launches Public Beta for Enhanced Content Evaluation

Oct 6, 2026

AI Summary

The Decisions API, now in public beta, offers faster evaluations of text and images, returning results about ten times quicker than the previous Responses API. It allows users to classify content, route requests, and prioritize tasks based on various answer types, with expectations for general availability in the coming weeks.

The Decisions API evaluates text, images, or both, providing answers significantly faster than the Responses API.
It can return probabilities for conditions, fixed choices, or scores against a rubric, aiding in content classification and request routing.
The API is currently available in public beta, with plans for general availability soon.
The only model available is gpt-6-luna, accessed via the dedicated POST /v1/decisions endpoint.
Users can experiment with the API in the Playground before implementing it in their applications.
Supported SDK versions include Python 3.26.0, JavaScript 7.30.0, Go 3.73.0, Ruby 0.101.0, and Java 4.78.0.
The API requires unique names for questions to identify answers in the response, and it supports both choice and score types for different evaluation needs.
Images must be provided as inline base64 data URLs, and the API does not support hosted image URLs or file IDs.

apipublic betadecisionsopenaidevelopers

Decisions API Launches Public Beta for Enhanced Content Evaluation

Related Stories

Sophos reduces cyber-threat investigation time significantly using OpenAI Daybreak

Website Simulates Elizabeth Holmes' Desk with Court Documents from Theranos Trial

Jev, an AI for making quick decisions, has been a viral hit in Silicon Valley. But OpenAI is hot on its heels

Google introduces Gemini AI with task management capabilities for businesses