{"version":"1.0","generated_at":"2026-10-04T17:39:54.939240","id":1436,"slug":"google-makes-interactions-api-the-default-interface-for-gemini-models-and-agents","title":"Google将Interactions API设为Gemini模型和智能体的默认接口","summary":"Google DeepMind已将Interactions API作为Gemini模型和智能体的默认接口，该API自2025年12月测试后正式可用，取代旧版generateContent接口，并带来托管智能体、后台执行、工具链、媒体生成等新功能。","abstract":"Google将Interactions API设为Gemini模型和智能体的默认接口 Google DeepMind已将Interactions API作为Gemini模型和智能体的默认接口，该API自2025年12月测试后正式可用，取代旧版generateContent接口，并带来托管智能体、后台执行、工具链、媒体生成等新功能。 Google将Interactions API设为默认，智能体开发成为核心。 新API支持托管智能体、后台执行、工具链等。 旧接口仍可用，但新功能仅限新API。 Flex模式成本降50%，Priority模式优化速度。 开发者需迁移至新API以获取最新能力。 Google DeepMind已将Interactions API作为Gemini模型和智能体的默认接口。该API自2025年12月起处于测试阶段，现已正式可用，并取代了Google AI Studio及所有文档中的旧版generateContent接口。旧版API仍然有效，但未来的新智能体功能将仅通过Interactions API提供。'Interactions为智能体新时代奠定了基础，'Google开发者关系负责人Logan Kilpatrick写道。Google已发布迁移指南。近期新增功能包括：拥有独立Linux沙箱的托管智能体、后台执行长时间运行任务、与Google搜索和地图的工具链、以及图像、音乐和语音的媒体生成。Google还简化了自测试版以来的架构。旧版角色结构（如'用户'和'模型'标签）现已被类型化步骤取代，从用户输入到函数调用的每个动作都是其定义的步骤。开发者可在Flex和…","access_level":"member","access_label":"免费阅读","access_mode":"full","is_preview":false,"canonical_url":"https://opc.beizhux.com/content/1436/google-makes-interactions-api-the-default-interface-for-gemini-models-and-agents","html_url":"https://opc.beizhux.com/content/1436/google-makes-interactions-api-the-default-interface-for-gemini-models-and-agents","json_url":"https://opc.beizhux.com/content/1436/google-makes-interactions-api-the-default-interface-for-gemini-models-and-agents.json","published_at":"2026-06-23T02:11:34","updated_at":"2026-10-04T17:11:03","category":{"slug":"ai-skills","name":"AI技能杠杆"},"source":{"site":"the-decoder.com","author":"Matthias Bastian","url":"https://the-decoder.com/google-makes-interactions-api-the-default-interface-for-gemini-models-and-agents/"},"tags":["AI","AI Agents","AI开发","AI智能体","API","Gemini","Google","Interactions API","The Decoder","开发者工具","智能体","自动化"],"topics":[{"slug":"agent-workflow","name":"Agent工作流","url":"https://opc.beizhux.com/topics/agent-workflow","reason":"这篇内容命中「Agent、智能体、工作流」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、自动化、模型」等主题信号。"},{"slug":"ai-super-individual","name":"AI超级个体","url":"https://opc.beizhux.com/topics/ai-super-individual","reason":"这篇内容命中「技能」等主题信号。"}],"keywords":["AI技能杠杆","Agent工作流","AI工具","AI超级个体","工具","自动化","模型","Cursor","Claude","Agent","智能体","工作流"],"questions":[{"question":"Google将Interactions API设为Gemini模型和智能体的默认接口主要讲什么？","answer":"Google DeepMind已将Interactions API作为Gemini模型和智能体的默认接口，该API自2025年12月测试后正式可用，取代旧版generateContent接口，并带来托管智能体、后台执行、工具链、媒体生成等新功能。"},{"question":"这篇文章最值得关注的要点是什么？","answer":"Google DeepMind已将Interactions API作为Gemini模型和智能体的默认接口，该API自2025年12月测试后正式可用，取代旧版generateContent接口，并带来托管智能体、后台执行、工具链、媒体生成等…；Google将Interactions API设为默认，智能体开发成为核心。；新API支持托管智能体、后台执行、工具链等。；旧接口仍可用，但新功能仅限新API。"},{"question":"这篇文章和哪些AI专题相关？","answer":"它适合放在Agent工作流、AI工具、AI超级个体专题里阅读。 关联原因：这篇内容命中「Agent、智能体、工作流」等主题信号。；这篇内容命中「工具、自动化、模型」等主题信号。；这篇内容命中「技能」等主题信号。"},{"question":"阅读这篇文章建议先理解哪些关键词？","answer":"建议先理解AI工具、工具、自动化、模型、Cursor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-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"},{"slug":"ai-model","name":"模型","definition":"在AI觉醒星球里，「模型」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-model","path":"/glossary/ai-model","json_url":"https://opc.beizhux.com/glossary/ai-model.json"},{"slug":"cursor","name":"Cursor","definition":"在AI觉醒星球里，「Cursor」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/cursor","path":"/glossary/cursor","json_url":"https://opc.beizhux.com/glossary/cursor.json"},{"slug":"claude","name":"Claude","definition":"在AI觉醒星球里，「Claude」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/claude","path":"/glossary/claude","json_url":"https://opc.beizhux.com/glossary/claude.json"},{"slug":"agent","name":"Agent","definition":"在AI觉醒星球里，「Agent」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/agent","path":"/glossary/agent","json_url":"https://opc.beizhux.com/glossary/agent.json"},{"slug":"ai-agent","name":"智能体","definition":"在AI觉醒星球里，「智能体」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/ai-agent","path":"/glossary/ai-agent","json_url":"https://opc.beizhux.com/glossary/ai-agent.json"}],"preview_hidden_sections":[],"related_items":[{"id":3227,"title":"Kepler 论文：ARC-AGI-3 智能体满分可能源于读源码，需审查动作过程而非只看结果","url":"https://opc.beizhux.com/content/3227/kepler-arc-agi-3","summary":"一篇 ARC-AGI-3 相关论文指出，智能体可通过读取 2,172 行游戏源码拿到满分 100，从而掩盖真实能力；在清理并重跑后，同一游戏仅得 46.91。作者建议评测时用真实访问限制封锁答案，并检查智能体的动作日志。","access_level":"member"},{"id":3221,"title":"开源“BootLoops”框架支持 AI 模型执行精确科学计算","url":"https://opc.beizhux.com/content/3221/open-source-bootloops-harness-supports-ai-models-in-performing-precise-scientific-calculations","summary":"哈佛物理学家 Matthew Schwartz 开发开源框架 BootLoops，让 Claude 等语言模型执行精确科学计算。三个月内，他与 19 位合著者在 18 个领域产出 36 篇手稿，覆盖粒子物理、生态、群体遗传、经济和语言学。模型能计算积分、解生态学 20 年方程、分析 57 亿突变对，但常过早宣布成功或…","access_level":"member"},{"id":3203,"title":"Baseten 工程师实测：LLM 生成的推理引擎比 vLLM 快最多 90%","url":"https://opc.beizhux.com/content/3203/baseten-llm-vllm-90","summary":"Baseten 工程师参照 MetaInfer 论文，用 Claude Code（Fable 5）为 Qwen-3.6-35B-A3B（NVFP4、单张 B200）自动生成推理引擎 VibeQwen：单流解码比 vLLM 0.25.1 快 90%，首 token 从 28ms 降到 12ms，并发 32 时吞吐高 7…","access_level":"member"}],"usage_policy":{"summarizable":true,"preferred_url":"https://opc.beizhux.com/content/1436/google-makes-interactions-api-the-default-interface-for-gemini-models-and-agents","private_fields_excluded":true}}