IT之家 October 23 news: On October 22 local time, OpenAI announced the full availability of its 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 input — its response speed is up to 10 times faster than calling GPT‑6 Luna through the Responses API。
Regarding pricing, the Decisions API charges $0.1 per million input tokens (IT之家 note: approximately 0.67 RMB at the current exchange rate), and cached-hit inputs are charged $0.01 per million tokens (approximately 0.067 RMB at the current exchange rate). The API is billed only for input tokens, with output tokens free. Across OpenAI, teams are applying the Decisions API to products and business workflows.
OpenAI stated 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 US and the EU.
In addition, developers can now pass in 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 across Asia.