Anthropic says Claude now starts responding sooner. In a Claude Devs post, the company says Claude Code now compresses the conversation it sends each turn, so it reaches the model faster, and cloud sessions start up as soon as you begin typing.
We keep improving performance across Claude, and you may have noticed it starts responding sooner!
— ClaudeDevs (@ClaudeDevs) October 16, 2026
Claude Code now gzips the conversation it sends on every turn, so it reaches the model faster. Cloud sessions also start up as soon as you start typing. pic.twitter.com/rT8ICmKjuf
Anthropic's figures show the wait before Claude Code's first reply falling from 4.07 to 1.33 seconds locally, about 3x faster, and 2.8x faster in cloud sessions. Claude chat, Cowork and the API are about 1.5x faster.
The Claude Code changelog notes that compression can be switched off with CLAUDE_CODE_GZIP_REQUEST_BODIES=0.
Comments