[{"data":1,"prerenderedAt":225},["ShallowReactive",2],{"copy:zh:site:":3,"copy:zh:cost:":123,"copy:zh:models:ui":189,"copy:zh:site:common":223},{"common":4,"nav":16,"footer":44,"home":51,"error":116},{"skip":5,"menu":6,"language":7,"sections":8,"footer":9,"tool":10,"home":11,"breadcrumbs":12,"copy":13,"copied":14,"download":15},"跳转到正文","菜单","语言","章节","页脚","工具","首页","面包屑导航","复制","已复制","下载",{"groups":17,"items":25},{"build":18,"connect":19,"instruct":20,"run":21,"web":22,"secure":23,"track":24},"构建","连接","编写指令","运行","开放你的网站","安全","跟踪",{"models":26,"cost":27,"frameworks":28,"mcp":29,"mcpConfig":30,"mcpClients":31,"agentsMd":32,"files":33,"openclaw":34,"agentReady":35,"llmsTxt":36,"robotsTxt":37,"apiCatalog":38,"bots":39,"security":40,"incidents":41,"checklist":42,"changelog":43},"模型与 API 价格","Agent 成本计算器","框架与 SDK","MCP 服务器","MCP 配置生成器","MCP 客户端","AGENTS.md 生成器","指令文件","自托管 OpenClaw","适配 Agent 的网站","llms.txt 生成器","面向 AI 机器人的 robots.txt","API 目录生成器","AI 机器人目录","Agent 安全","事故记录","安全检查清单","更新日志",{"about":45,"privacy":46,"terms":47,"sitemap":48,"disclaimer":49,"checked":50},"关于","隐私","条款","网站地图","为 AI agent 开发者提供的独立参考资料。与此处提及的任何厂商均无关联。","事实核查日期：{date}",{"seo":52,"eyebrow":55,"title":56,"lead":57,"ctaMcp":58,"ctaCost":59,"ctaAgents":60,"sheetLabel":61,"sheetTitle":62,"sheet":63,"sheetNote":69,"sectionsTitle":70,"sections":71,"latestTitle":99,"allChanges":100,"rulesTitle":101,"rules":102,"aboutLink":115},{"title":53,"description":54},"DotsAgent：构建 AI agent 的参考资料与工具","LLM API 价格、agent 成本计算器、适用于 13 个客户端的 MCP 配置、AGENTS.md 和 llms.txt 生成器，以及 agent 安全指南。免费提供，支持 18 种语言。","面向 AI agent 开发者","Agent 开发者的案头参考","涵盖 agent 开发所需的价格、协议、配置文件和安全指南，所有信息均经厂商官方文档核实。查找信息、生成所需文件，然后继续编写代码。","生成 MCP 配置","计算 agent 任务成本","编写 AGENTS.md","最新数据","技术栈概览",{"mcp":64,"openclaw":65,"cheapest":66,"models":67,"servers":29,"bots":68},"MCP 规范","OpenClaw","最低价模型，$\u002F百万输入\u002F输出 tokens","已统计价格的模型","已跟踪的 AI 机器人","每项数据均经人工对照厂商文档核实。","网站内容",{"models":72,"mcp":76,"instructions":79,"frameworks":82,"openclaw":85,"agentReady":88,"security":92,"changelog":95},{"title":73,"body":74,"unit":75},"模型与价格","并列比较每百万输入、输出和缓存 token 的价格，并提供计算器，估算完整 agent 运行的费用。","个模型",{"title":29,"body":77,"unit":78},"Model Context Protocol 服务器目录，以及配置生成器，可为每种客户端生成对应的配置文件。","台服务器",{"title":33,"body":80,"unit":81},"编写 AGENTS.md，并了解各工具如何读取 CLAUDE.md、.cursor\u002Frules 等类似文件。","种文件格式",{"title":28,"body":83,"unit":84},"按语言、许可证、MCP 支持和多 agent 功能对比 agent 框架与厂商 SDK。","个框架",{"title":34,"body":86,"unit":87},"逐步指导你在自己的设备或服务器上安装、配置和更新 OpenClaw。","当前版本",{"title":89,"body":90,"unit":91},"适配 agent 的网站","生成 llms.txt、面向 AI crawler 的 robots.txt 规则和 api-catalog，并通过 user agent 查询任意机器人。","个已收录机器人",{"title":40,"body":93,"unit":94},"了解 agent 面临的 OWASP 风险、真实事件记录，以及上线前可逐项核对的清单。","起已记录事件",{"title":96,"body":97,"unit":98},"API 更新日志","按日期记录模型 API、SDK 和协议的变更，并附上厂商公告链接。","条记录","最新变更","所有变更","我们如何确保信息准确",[103,106,109,112],{"title":104,"body":105},"事实均有来源。","每项价格、版本和 flag 都链接到对应的供应商页面，方便你自行核实。",{"title":107,"body":108},"定期核查。","每个页面都会显示上次核查信息的时间；过时的条目会重新核查或移除。",{"title":110,"body":111},"不接受付费推广。","没有人能付费获得收录、提高排名或得到更好的描述。",{"title":113,"body":114},"工具在浏览器中运行。","生成器和计算器都在本地运行，你输入的内容不会发送到服务器。","关于 DotsAgent",{"title":117,"body":118,"home":119,"popular":120,"failed":121,"failedBody":122},"找不到页面","此地址没有对应的页面。页面可能已迁移，或者链接中有拼写错误。","前往首页","热门工具","出了点问题","我们这边未能加载此页面。请稍后再试，或从首页开始浏览。",{"seo":124,"crumb":127,"eyebrow":128,"title":127,"lead":129,"presets":130,"form":147,"table":162,"method":169,"faqTitle":175,"faq":176},{"title":125,"description":126},"AI 智能体成本计算器：计算 28 款模型的任务费用","估算 28 个 LLM API 上单个智能体任务和每月任务的费用。设置提示词大小、上下文增长量、步骤数、输出量和缓存命中率；包含长提示词费率。","智能体成本计算器","构建 · 工具","智能体由循环驱动：每次调用都会重新发送此前的全部内容，以及最新的工具结果。只需描述一次这个循环，即可查看我们的价格表中每款模型执行单个任务和每月任务的费用。",{"support":131,"coding":135,"browser":139,"research":143},{"name":132,"shape":133,"about":134},"客服机器人","{steps} 次调用，简短的工具查询","通过查询订单或帮助文章来回答客户问题：提示词精简，进行几次工具调用，并给出简短回复。",{"name":136,"shape":137,"about":138},"编程智能体","{steps} 次调用，文件和测试输出","读取文件、修改代码并在 repository 中运行测试。系统提示词包含大量内容和工具 schema，每个步骤都会增加一个文件或一段测试日志。",{"name":140,"shape":141,"about":142},"浏览器智能体","{steps} 次调用，截图和网页文本","浏览网站以填写表单或收集价格。每个步骤都会增加一张截图或一段页面内容，而每次回复都是简短的操作指令。",{"name":144,"shape":145,"about":146},"研究智能体","{steps} 次调用，较长的搜索结果","搜索网页、阅读资料并撰写报告。搜索结果较长，且只有部分内容会重复，因此缓存的帮助较小。",{"preset":148,"base":149,"baseHint":150,"growth":151,"growthHint":152,"steps":153,"stepsHint":154,"output":155,"outputHint":156,"cacheHit":157,"cacheHitHint":158,"perDay":159,"provider":160,"summary":161},"从工作负载开始","初始提示词，token 数","系统提示词、工具定义和任务本身。","每步新增 token 数","工具结果和模型上一轮的回复。","每个任务的模型调用次数","循环在完成任务前调用模型的次数。","每次调用的输出 token 数","包括推理 token；它们按输出计费。","提示词缓存命中率","首次调用后，每次 prompt 中命中服务商缓存的比例。","每天的任务数","显示服务商","每个任务发送 {input} 个输入 token，并接收 {output} 个输出 token。单个 prompt 的最大长度为 {peak} 个 token。",{"caption":163,"perTask":164,"perMonth":165,"overflow":166,"longCalls":167,"legend":168},"各模型的单任务和月度预估费用","每个任务","按每天 {n} 个任务计算 30 天","超过上下文窗口","{n} 次调用按长 prompt 费率计费","标价，标准档位，美元。不含缓存写入、税费、网页搜索等工具费用及地区附加费。",{"title":170,"body":171,"limits":174},"估算方法",[172,173],"对于循环中的每次调用，我们会根据 prompt 大小计算费用：prompt 大小由首个 prompt 加上此前每一步增加的内容组成，并拆分为缓存部分和未缓存部分。首次调用始终按未缓存部分计算。未缓存 token 按输入费率计费，缓存 token 按缓存费率计费，输出 token 则按输出费率计费。","如果单个 prompt 超过服务商的长上下文阈值，整次调用都会按长 prompt 费率计费，OpenAI、Google、xAI 和 Qwen 都采用这种方式。如果最大 prompt 超出模型的上下文窗口，表格会标记该行，因为实际使用时，agent 必须先精简或总结历史记录。","实际 agent 的任务各不相同，也会重试失败的步骤，有时还会提前停止。请将这些数据用于比较同一工作负载下的不同模型；制定预算前，请先根据自己的运行记录测量实际 token 用量。","关于 agent 成本的常见问题",[177,180,183,186],{"q":178,"a":179},"AI agent 每个任务会使用多少 token？","这主要取决于步骤数以及每一步新增的内容。简短的客服对话可能使用 30K 个输入 token；如果是从 25K-token 初始 prompt 开始的 30 步编程任务，输入量会超过三百万个 token，因为每次调用都会重新发送完整历史记录。",{"q":181,"a":182},"如何降低 agent 的成本？","确保各次调用的 prompt 开头保持一致，以便命中缓存；将工具结果精简到模型所需的内容；总结或删除较早的对话轮次；日常步骤使用小模型，仅在规划时使用大模型；在质量允许的情况下，降低推理强度。",{"q":184,"a":185},"prompt 缓存会自动生效吗？","对于 OpenAI、DeepSeek、Kimi 和 Gemini 的隐式缓存，只要 prompt 共用较长的前缀，缓存就会自动生效。Anthropic 和部分 Qwen endpoint 需要显式添加缓存标记；Anthropic 首次写入缓存还会收取额外费用。",{"q":187,"a":188},"为什么每个 token 价格最低的模型，每个任务的成本却不一定最低？","不同模型的缓存折扣各不相同，有些服务商会对长 prompt 按更高费率计费，而推理模型会消耗输出 token 进行思考。如果某个模型所需步骤更少或重试更少，成本也可能更低；此计算器无法体现这些因素。",{"ui":190},{"crumb":191,"sources":192,"filters":193,"tiers":198,"table":202,"flags":211,"caps":215},"模型","来源",{"provider":194,"tier":195,"all":196,"anyTier":197},"按提供商筛选","按级别筛选","所有提供商","所有级别",{"flagship":199,"mid":200,"small":201},"旗舰","主力","小型高速",{"caption":203,"model":191,"provider":204,"input":205,"cached":206,"output":207,"context":208,"released":209,"perM":210},"用于构建智能体的模型 API 标价","提供商","输入","缓存输入","输出","上下文","发布时间","每百万 token 的美元价格；标准级别、短 prompt 费率",{"preview":212,"thirdParty":213,"long":214},"预览版","第三方价格","长 prompt 费用更高",{"tools":216,"structured":217,"computerUse":218,"mcp":219,"webSearch":220,"reasoning":221,"vision":222},"工具调用","结构化输出","计算机操作","远程 MCP","内置网页搜索","可调节推理","图像输入",{"common":224},{"skip":5,"menu":6,"language":7,"sections":8,"footer":9,"tool":10,"home":11,"breadcrumbs":12,"copy":13,"copied":14,"download":15},1790863379699]