OpenAI Decisions API
A low-latency, end-to-end decision-making API introduced by OpenAI, described as completing decisions in under a few hundred milliseconds. It targets use cases requiring millisecond-level response times, such as game AI and real-time risk control.
Core Facts
Timeline (last 90 days)
Once the model resides in memory, the response speed of local Ollama is roughly more than twice that of the cloud OpenAI Decisions API.
The OpenAI Decisions API (gpt-6-luna) was released on October 6, with an input price of $0.10 / 1M tokens, free output, closed source, and an undisclosed context length.
OpenAI claims the Decisions API is 10 times faster than the Responses API, but attaches no benchmark data; Microsoft and other vendors have not published latency data.
In pure text classification tasks, Ollama is fastest at approximately 1.1 seconds, OpenAI Decisions API at approximately 2.5 seconds, and Jev at approximately 2.9 seconds.
Following TypeSafe's Jev and the open-weight Laya model, decision-oriented products such as AWS Strands Decider, Cloudflare Clef, and OpenAI's Decisions API have successively emerged.
OpenAI launched a product called the Decisions API.
All Facts (3)
OpenAI launched a product called the Decisions API.
75%UnverifiedOnce the model resides in memory, the response speed of local Ollama is roughly more than twice that of the cloud OpenAI Decisions API.
50%UnverifiedFollowing TypeSafe's Jev and the open-weight Laya model, decision-oriented products such as AWS Strands Decider, Cloudflare Clef, and OpenAI's Decisions API have successively emerged.
50%