AI BriefingHow message threads reduce latency for long-running agents
·2026.11.02 09:00
Key point
The feature reduces time to first token by sending only new messages since the last turn, with threads held in encrypted memory and expiring after 5 minutes of inactivity.
Details
- Message threads is now available in public beta on the Claude Platform, allowing agents to send only new messages since the last turn instead of resending full conversation history.
- For requests with 500k to 1M tokens, median time to first token (TTFT) drops by about 35% when message threads is enabled.
- Threads are held in encrypted memory and expire 5 minutes after the last request; token usage remains unchanged because Claude still reads the full conversation on every turn.
- The feature is best suited for long-running coding agents, computer use agents, and document or image-heavy workflows where latency is a primary concern.
- Available on the native Claude Platform, Claude Platform on AWS, Claude in Microsoft Foundry, and Claude Models on Google Cloud (Anthropic managed) with standard token rates and existing rate limits applying.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Anthropic restricts Claude from reverse-engineering video gamesAnthropic's internal AI usage value exceeds employee compensation