LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · OpenAI决策接口Material3 min de leituraEditorial DisconfirmAI

OpenAI Fully Opens Decisions API: Millisecond-Level Decision-Making Based on GPT-6 Luna Targets Fast, Low-Cost AI Market

OpenAI has officially opened its Decisions API to all customers. Optimized based on GPT-6 Luna, the interface reduces response times for certain tasks to 100-180 milliseconds, aiming to lower AI decision-making costs and accelerate agent application deployment.

2026-10-23 16:21 GMT+8

According to a report by TechCrunch cited by Zhidongxi, OpenAI officially opened its Decisions API to all customers on October 22. The interface is optimized based on the reasoning model GPT-6 Luna and primarily targets tasks with defined answer ranges, such as content classification, request routing, and determining the next action of an AI agent. Developers can pre-set questions and optional answers, from which the model outputs probabilities, options, or scores.

Nikunj Handa, Head of Product for OpenAI's API, stated that after observing Jev, a decision model launched by AI startup TypeSafe, the team realized the significant potential application scenarios for such models. Instead of training a dedicated decision model from scratch, OpenAI adjusted the inference method of the existing base reasoning model GPT-6 Luna to significantly shorten response times and reduce costs. Handa noted that response times for some tasks have been reduced from 1-3 seconds to 100ms, 120ms, or 180ms.

In terms of functional specifications, the Decisions API supports text, image, and structured data inputs, handling up to 400 questions per request—double the limit during the previous public testing phase. OpenAI announced the interface at its developer day event on September 29, began public testing on October 6, and declared full availability on October 22.

OpenAI showcased several enterprise customer use cases, claiming they demonstrate the interface's advantages in speed and cost. Cloud monitoring platform Datadog uses the Decisions API to assess risks of commands generated by AI agents, reporting P95 latency approximately 40 times faster than available frontier models; financial management platform Ramp reported a 4x increase in processing speed and a 30% reduction in costs; language learning platform Speak reduced wait times between user operations from 1.4 seconds to 0.13 seconds. It should be noted that these performance figures are self-reported results from customers showcased by OpenAI and have not been verified by independent third-party large-scale benchmark reproductions.

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento

The launch signals intensifying competition in the AI decision model space. TypeSafe AI released its first System One model, Jev, on September 15, specifically designed to make quick judgments based on preset options and provide confidence levels. While TypeSafe's internal tests showed Jev achieved 68% accuracy across 8 workflow tests, third-party rankings vary: AIMultiple's System One Index ranks Jev 7th and OpenAI's Decisions API 14th; Artificial Analysis's Decision Index ranks Jev 2nd and OpenAI 11th. Additionally, Opper AI's JevMan benchmark test shows Jev 1.14 scoring higher on average than OpenAI's GPT-6 Luna.

Handa indicated that OpenAI may conduct specialized training for these tasks in the future to further improve performance, currently achieving capabilities mainly through adjustments to the existing Luna model. He believes that if interface response times can be further shortened to around 60 milliseconds, developers could call the interface on every frame of video to make real-time decisions, thereby expanding more application scenarios.

Fontes

  • zhidx.com↗
Tópico

OpenAI决策接口

OpenAI推出Decisions API,旨在通过GPT-6 Luna模型提供毫秒级、低成本的分类与决策服务,直接对标TypeSafe的Jev模型。该接口支持文本和图像输入,将响应时间从秒级压缩至百毫秒级,并简化了计费模式。尽管在部分基准…

3 etapas5 peçasAtualizado 2026-10-25 19:41

Como chegamos aqui

  1. 2026-09-30OpenAI CEO Sam Altman在DevDay上首次透露Decisions API,称其功能类似TypeSafe的Jev,用于快速低成本分类。techcrunch.com ↗
  2. 2026-10-06OpenAI发布Decisions API公测版,基于gpt-6-luna模型,支持图像输入,按输入token计费。simonwillison.net ↗
  3. 2026-10-22OpenAI正式向所有客户开放Decisions API,推理延迟降至100-180毫秒,并新增GPT-Live原生集成等功能。openai.com ↗

O que ainda está indefinido

  • 在AIM System One Index等公开基准测试中,OpenAI Decision Model排名低于Liquid的D1 Ultra和Base Lab的Elephant-1,其实际生产环境中的校准度如何?
  • TypeSafe CEO Diogo Almeida强调合成数据是护城河,OpenAI依靠Luna模型的通用能力能否在特定决策任务上长期保持成本效益优势?
  • 随着延迟进一步降低至60毫秒以下,是否会催生如视频帧级实时决策等新用例,从而改变现有智能体架构?

Também nesta thread

  • OpenAI Makes Decisions API Widely Available, Cutting Latency to Sub-Second Levels2026-10-23
  • OpenAI Releases Image-Supporting Decisions API2026-10-07
Ler o tópico completo →
Continuar pesquisando →