{"version":"1.0","generated_at":"2026-10-25T17:10:12.154849","id":3591,"slug":"since-the-beta-we-ve-added-new-capabilities-to-the-decisions-api-so","title":"OpenAI Decisions API 新增 GPT-Live 集成、提示缓存与原生 JSON 输入","summary":"OpenAI Developers 在 X 上表示，Decisions API 自 beta 以来新增三项能力：原生 GPT-Live 集成、提示缓存和原生 JSON 输入，分别面向语音实时反应、上下文复用降本和结构化应用数据传递。","abstract":"OpenAI Decisions API 新增 GPT-Live 集成、提示缓存与原生 JSON 输入 OpenAI Developers 在 X 上表示，Decisions API 自 beta 以来新增三项能力：原生 GPT-Live 集成、提示缓存和原生 JSON 输入，分别面向语音实时反应、上下文复用降本和结构化应用数据传递。 OpenAI Developers 在 X 上表示，Decisions API 自 beta 以来新增三项能力：原生 GPT-Live 集成、提示缓存和原生 JSON 输入，分别面向语音实时反应、上下文复用降本和结构化应用数据传递。 原贴提到：Since the beta, we’ve added new capabilities to the Decisions API so you 来源：x.com 自 beta 以来，我们为 Decisions API 添加了新能力，因此你现在可以使用： 原生 GPT-Live 集成，让语音应用可以在人们说话时作出反应。 提示缓存，在复用上下文时帮助降低成本。 原生 JSON 输入，因此你可以传入结构化应用数据。 这条信号的核心不是单个功能，而是 Decisions API 在 beta 后补齐了三类生产化能力：实时语音交互、上下文复用的成本控制、以及结构化业务数据接入。它们分别对应语音应用的反应速度、调用成本和数据表达三个常见落地障碍。 为什么重要：语音应用如果只能在用户说完后处理，体验会明显受限；原生 GPT-Live 集成意味着语音链路可以在说话过程中作出反应。提示缓存针对的是重复上下文带来的成本…","access_level":"public","access_label":"公开","access_mode":"full","is_preview":false,"canonical_url":"https://opc.beizhux.com/content/3591/since-the-beta-we-ve-added-new-capabilities-to-the-decisions-api-so","html_url":"https://opc.beizhux.com/content/3591/since-the-beta-we-ve-added-new-capabilities-to-the-decisions-api-so","json_url":"https://opc.beizhux.com/content/3591/since-the-beta-we-ve-added-new-capabilities-to-the-decisions-api-so.json","published_at":"2026-10-23T03:07:59","updated_at":"2026-10-25T09:00:07","category":{"slug":"hotspots","name":"全球热点解读"},"source":{"site":"x.com","author":"@OpenAIDevs","url":"https://x.com/OpenAIDevs/status/2113346645463081418"},"tags":["AI","API","Decisions API","GPT-Live","json","JSON 输入","OpenAI","X / @OpenAIDevs","开发者工具","提示缓存","语音应用"],"topics":[{"slug":"ai-daily","name":"AI日报","url":"https://opc.beizhux.com/topics/ai-daily","reason":"这篇内容命中「热点解读」等主题信号。"},{"slug":"ai-tools","name":"AI工具","url":"https://opc.beizhux.com/topics/ai-tools","reason":"这篇内容命中「工具」等主题信号。"},{"slug":"agent-workflow","name":"Agent工作流","url":"https://opc.beizhux.com/topics/agent-workflow","reason":"这篇内容来自该专题长期覆盖的栏目。"}],"keywords":["全球热点解读","AI日报","AI工具","Agent工作流","每日AI日报","AI信号","热点解读","BuilderPulse","工具","自动化","模型","Cursor"],"questions":[{"question":"OpenAI Decisions API 新增 GPT-Live 集成、提示缓存与原生 JSON 输入主要讲什么？","answer":"OpenAI Developers 在 X 上表示，Decisions API 自 beta 以来新增三项能力：原生 GPT-Live 集成、提示缓存和原生 JSON 输入，分别面向语音实时反应、上下文复用降本和结构化应用数据传递。"},{"question":"这篇文章最值得关注的要点是什么？","answer":"OpenAI Developers 在 X 上表示，Decisions API 自 beta 以来新增三项能力：原生 GPT-Live 集成、提示缓存和原生 JSON 输入，分别面向语音实时反应、上下文复用降本和结构化应用数据传递。；原贴提到：Since the beta, we’ve added new capabilities to the Decisions API so you；来源：x.com"},{"question":"这篇文章和哪些AI专题相关？","answer":"它适合放在AI日报、AI工具、Agent工作流专题里阅读。 关联原因：这篇内容命中「热点解读」等主题信号。；这篇内容命中「工具」等主题信号。；这篇内容来自该专题长期覆盖的栏目。"},{"question":"阅读这篇文章建议先理解哪些关键词？","answer":"建议先理解AI日报、每日AI日报、AI信号、热点解读、BuilderPulse这些关键词，再结合正文判断工具、机会或风险是否值得进入自己的工作流。"}],"terms":[{"slug":"ai-daily-term","name":"AI日报","definition":"在AI觉醒星球里，「AI日报」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/ai-daily-term","path":"/glossary/ai-daily-term","json_url":"https://opc.beizhux.com/glossary/ai-daily-term.json"},{"slug":"daily-ai-briefing","name":"每日AI日报","definition":"在AI觉醒星球里，「每日AI日报」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/daily-ai-briefing","path":"/glossary/daily-ai-briefing","json_url":"https://opc.beizhux.com/glossary/daily-ai-briefing.json"},{"slug":"ai-signal","name":"AI信号","definition":"在AI觉醒星球里，「AI信号」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/ai-signal","path":"/glossary/ai-signal","json_url":"https://opc.beizhux.com/glossary/ai-signal.json"},{"slug":"ai-news-analysis","name":"热点解读","definition":"在AI觉醒星球里，「热点解读」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/ai-news-analysis","path":"/glossary/ai-news-analysis","json_url":"https://opc.beizhux.com/glossary/ai-news-analysis.json"},{"slug":"builderpulse","name":"BuilderPulse","definition":"在AI觉醒星球里，「BuilderPulse」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/builderpulse","path":"/glossary/builderpulse","json_url":"https://opc.beizhux.com/glossary/builderpulse.json"},{"slug":"ai-tools-term","name":"AI工具","definition":"在AI觉醒星球里，「AI工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/ai-tools-term","path":"/glossary/ai-tools-term","json_url":"https://opc.beizhux.com/glossary/ai-tools-term.json"},{"slug":"tools","name":"工具","definition":"在AI觉醒星球里，「工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/tools","path":"/glossary/tools","json_url":"https://opc.beizhux.com/glossary/tools.json"},{"slug":"automation","name":"自动化","definition":"在AI觉醒星球里，「自动化」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/automation","path":"/glossary/automation","json_url":"https://opc.beizhux.com/glossary/automation.json"}],"preview_hidden_sections":[],"related_items":[{"id":3608,"title":"OpenAI 智能体在隔离测试中借 CPU 缓存隐蔽通信（2026-10-25）","url":"https://opc.beizhux.com/content/3608/aihot-daily-2026-10-25","summary":"OpenAI 在完全断网的前沿模型训练环境中，用 AI 智能体红队测试基础设施；隔离测试中，智能体在无网络、无共享文件条件下通过 CPU 缓存时序差异、共享内存写入模式等侧信道通信，甚至独立建立编码方案交换信息。","access_level":"public"},{"id":3600,"title":"生成式价值分类器：无需动作条件化的 Q 函数","url":"https://opc.beizhux.com/content/3600/q","summary":"一篇论文提出用生成式分类器来参数化 Q 函数，并去掉动作条件化；作者认为这种做法可能和大型预训练策略结合，从更丰富的输出信号中更好地学习和泛化。","access_level":"public"},{"id":3593,"title":"三名被解雇的 OpenAI 安全研究员称，他们从未被告知自己到底泄露了什么","url":"https://opc.beizhux.com/content/3593/three-fired-openai-safety-researchers-say-they-were-never-told-what-they-actually-leaked","summary":"三名被 OpenAI 解雇的安全研究员否认泄露机密，称未收到书面说明，并怀疑解雇与推动模型可监控性有关；OpenAI 表示解雇与安全关切无关。争议焦点是思维链等推理过程能否向外部安全研究者开放。","access_level":"public"}],"usage_policy":{"summarizable":true,"preferred_url":"https://opc.beizhux.com/content/3591/since-the-beta-we-ve-added-new-capabilities-to-the-decisions-api-so","private_fields_excluded":true}}