Anthropic Speeds Up Claude Code First Response by 3x

Anthropic announced major latency improvements: Claude Code's first response is now 3x faster and the API 1.5x faster, thanks to gzipped context, pre-started cloud sessions, and reduced pre-model processing that lowers first-token latency.

2026-10-17 ~ 2026-10-17 · 2 related posts

• Anthropic: Claude Code responds 3x faster, Claude API 1.5x faster via gzip and infra cuts — ClaudeDevs · 2026-10-17
• Anthropic details API speedup: trimmed pre-processing and no inbound buffering — ClaudeDevs · 2026-10-17