Anthropic 在 Claude 平台公测 Message Threads，长对话首 token 延迟降低约 35%
Anthropic's Message Threads cut time to first token by 35 percent for long conversations
Anthropic 在 Claude 平台以公开测试形式推出 Message Threads，API 请求不再重发完整对话历史，只传输上次消息之后的增量内容。据 Anthropic 数据，在 50 万至 100 万 token 的请求中，首 token 时间缩短约 35%。该功能对编码智能体、computer-use 智能体和处理大量文档或图像的工作流收益最大；线程在请求之间以加密形式保存在内存中，闲置五分钟后过期，token 用量不变，因为 Claude 仍会读取完整对话历史。该功能可在 Claude 平台以及 AWS、Microsoft Foundry 和 Google Cloud 上使用。
推荐理由
AI 评分 62
原文给出了首 token 延迟的降幅和适用场景，读者可据此判断长对话 Agent 的调用成本变化。
主题
正文
Anthropic released Message Threads as a public beta on its Claude platform. Until now, every API request had to resend the entire conversation history. Message Threads only transmits what's changed since the last message, cutting time to first token by about 35 percent for requests between 500,000 and one million tokens, according to Anthropic .
Coding agents, computer-use agents, and workflows processing lots of documents or images benefit the most, the company says. The thread stays encrypted in memory between requests and expires after five minutes of inactivity. Token usage doesn't change since Claude still reads the full conversation history. The feature works on the Claude platform and through AWS, Microsoft Foundry, and Google Cloud. Details are in the documentation .