Anthropic's Message Threads cut time to first token by 35 percent for long conversations
Summary
- Anthropic released Message Threads in public beta on the Claude platform to optimize long conversations.
- Instead of resending entire conversation histories, Message Threads transmits only changes since the last message.
- The feature reduces time to first token by roughly 35 percent for requests between 500k and one million tokens.
- Threads remain encrypted in memory and expire after five minutes of inactivity, supporting cloud integrations like AWS and Google Cloud.
Why it matters
Message Threads significantly improves latency for long-context applications like coding agents and document-heavy workflows without changing total token consumption.