OpenAI Fully Opens the Decisions API Based on GPT-6 Luna
OpenAI announced the full opening of the Decisions API built on GPT-6 Luna, aimed at questions with a limited set of answers, with response speeds up to 10 times faster than calling GPT-6 Luna through the Responses API. The API charges $0.10 per million input tokens, $0.01 per million cached input tokens, bills only for input tokens, and output tokens are free. Since the public beta, it has added native GPT-Live integration, prompt caching, and inference data residency support in the United States and the European Union, and up to 400 questions can be submitted per request.
Why read this
AI score 75
The original article provides the Decisions API's pricing, latency improvements, and new capabilities, so readers can judge which near-real-time decision scenarios it suits.
Topics
Body · AI translation
Based on GPT-6 Luna, OpenAI announces full opening of Decisions API IT Home Download the app for exclusive early access October 23, 2026, 07:49:32 From Shandong Updated October 23, 2026, 08:41:32
IT Home, October 23: On October 22 local time, OpenAI announced the full opening of the Decisions API.
According to the introduction, the API is built on GPT-6 Luna, focusing Luna's model intelligence on questions with bounded answers, helping applications and agents make near-real-time decisions based on text, images, and structured inputs — with response speeds up to 10 times faster than calling GPT-6 Luna through the Responses API.
In terms of pricing, the Decisions API charges $0.10 per million input tokens (IT Home note: approximately 0.67 yuan at current exchange rates), and $0.01 per million cached input tokens (approximately 0.067 yuan at current exchange rates). The API is billed only on input tokens; output tokens are free. Across OpenAI, teams are applying the Decisions API to product and business workflows.
OpenAI said that since the public beta, the feature has added native GPT-Live integration, Prompt caching for reused context, and inference data residency support in the United States and the European Union.
In addition, developers can now pass native JSON input, include images in question instructions, and submit up to 400 questions in a single request (twice the previous limit). OpenAI said it has continuously optimized latency performance, including expanding service capacity in multiple regions in Asia.
"Special statement: The above content (including videos, pictures, and audio if any) is uploaded and published by users of Dafeng Hao, a self-media platform under Phoenix Net. This platform only provides information storage space services.
Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."