Anthropic 在 Claude 平台公测 Message Threads，长对话首 token 时间降低约 35%
Anthropic's Message Threads cut time to first token by 35 percent for long conversations
AI 导读
Anthropic 在 Claude 平台推出 Message Threads 公测。
摘要与补充说明
此前每次 API 请求都要重发完整对话历史，新机制只传输上一条消息之后发生变化的部分，据 Anthropic 数据，50 万至 100 万 token 的请求首 token 时间降低约 35%。该功能对编码智能体、计算机使用智能体和处理大量文档或图像的工作流收益最大。线程在两次请求之间以加密形式保存在内存中，闲置 5 分钟后过期；由于 Claude 仍会读取完整对话历史，token 用量不变。该功能可在 Claude 平台以及 AWS、Microsoft Foundry 和 Google Cloud 上使用。
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.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.