AI Briefing#decisions-api
The latest AI and developer news about #decisions-api, with the original source and a short summary.
The latest AI and developer news about #decisions-api, with the original source and a short summary.
The feature searches the web before answering, raising accuracy on current-fact questions from 51% to 86% while keeping median latency under 400 ms.
The plugin provides Codex with codebase standards and cross-repository dependencies to identify critical issues before pull requests are opened.
The Decisions API supports up to 400 questions per request, while GPT-6.1 Terra offers fast work at roughly half the token cost of larger models.
OpenAI introduced Dots for background task automation and a Decisions API for quick AI actions, alongside expanded Codex capabilities.
Built with GPT-6 Luna, the API processes text, images, and JSON inputs to return probabilities, choices, or scores, now supporting up to 400 questions per request and native GPT-Live integration.
The API supports decision models like GPT-6 Luna Decisions and requires OpenAI SDK 7.30.0+ (JS) or 3.26.0+ (Python).
A new benchmark reveals that GPT-6 Luna, the model powering OpenAI's upcoming Decisions API, exhibits severe overconfidence and accuracy drops on multi-step reasoning tasks.
Currently testing with selected customers, with plans to expand access within a few days.