# Claude Code's message threads cut first-token latency about 35% on long requests

> Original title: We recently integrated message threads in Claude Code. On requests with 500K to 1M tokens, median time to first token is about 35% lower.

- Source: ClaudeDevs
- Published: 2026-11-02T19:06:09.000Z
- Bad Influence: https://badinfluence.news/items/uixbs4xkqfhdwol8v8ktowb6l
- Original: https://x.com/ClaudeDevs/status/2117332451231956997

## Summary

Anthropic says its recently integrated message threads in Claude Code reduce median time to first token by about 35% on requests with 500K to 1M tokens. In long conversations, the median request size dropped from about 800 KB to 1.8 KB.

## Post

We recently integrated message threads in Claude Code. On requests with 500K to 1M tokens, median time to first token is about 35% lower.

In long conversations, the median request went from about 800 KB to 1.8 KB.