Anthropic 优化 Claude API 降低首 token 延迟
On the API side, we cut the work the Messages API does before your request reaches the model, which lowered time to first token. Requests are also no longer buf
AI 导读
Anthropic 的 ClaudeDevs 账号介绍 Claude 性能改进：Claude Code 现在对每轮发送的对话内容做 gzip 压缩，使其更快到达模型；云会话在你开始输入时即启动。在 API 侧，Messages API 在请求到达模型前所做的工作被削减，降低了首 token 延迟，请求在传入时也不再被缓冲，此外还有一系列较小的基础设施改进。
正文
当前显示原文，中文全文译文尚未就绪。
On the API side, we cut the work the Messages API does before your request reaches the model, which lowered time to first token. Requests are also no longer buffered on their way in, on top of a long list of smaller infra improvements.