Skip to content
NewA calmer, faster ZeroHour

Anthropic's Message Threads cut time to first token by 35 percent for long conversations

The Decoderby Matthias Bastian ()1 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

Message Threads on Claude platform transmits only changed content since last message, reducing time to first token by 35 percent for long conversations.

Anthropic released Message Threads as a public beta on its Claude platform. Requests now only transmit what's changed since the last message, cutting time to first token by about 35 percent for conversations between 500,000 and one million tokens. The thread stays encrypted in memory between requests and expires after five minutes of inactivity. It works on the Claude platform and through AWS, Microsoft Foundry, and Google Cloud. Token usage does not change since Claude still reads the full conversation history. The feature benefits coding agents, computer-use agents, and workflows processing lots of documents or images.

Key facts
  • Cuts time to first token by 35 percent for 500,000 to 1 million token conversations
  • Thread encrypted in memory and expires after five minutes of inactivity
  • Feature available on Claude platform, AWS, Microsoft Foundry, and Google Cloud
  • No change in token usage as full history is still read by Claude
  • Benefits coding agents, computer-use agents, and document or image processing workflows
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at the-decoder.com

Anthropic released Message Threads for the Messages API. Instead of resending the entire conversation with every turn, agents now only transmit what's changed. For requests between 500,000 and one million tokens, time to first token drops by about 35 percent.

The Decoder

By Matthias Bastian · the-decoder.com

Read the full article at The Decoder

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.