Back to Devoured - November 03, 2026
DEVOURED
Claude Introduces Message Threads

Claude Introduces Message Threads

AI llmbackend Claude
Anthropic's new 'Message Threads' for the Messages API reduces time-to-first-token by 35% by eliminating the need to resend full conversation histories.
What: The new feature allows developers to send only the new delta of a conversation rather than the entire context on every turn. While tokens are still processed, the reduction in payload size significantly lowers latency for active coding and agentic workflows.
Why it matters: Latency is the primary bottleneck for agentic systems that require hundreds of turns, and this API optimization moves closer to the performance required for real-time, interactive AI coding agents.
Takeaway: If you are building long-running coding agents using the Messages API, adopt the 'thread' parameter to optimize your application's responsiveness.
Decoder
  • Time to first token (TTFT): A critical performance metric for LLM APIs that measures the duration between sending a request and receiving the first segment of the generated response.
Original article

Message threads is now available in public beta on the Claude Platform. With message threads, agents no longer need to resend the full conversation history on every turn, reducing latency for long-running sessions.

How message threads works

A coding agent might make hundreds of requests in one session, and each request resends every earlier message and tool result. Once a conversation reaches hundreds of thousands of tokens, resending all of it adds time before Claude starts responding. With message threads, agents send only what’s new since the last turn, which reduces time to first token (TTFT).

With message threads on by default for most Claude Code users, requests with 500k to 1M tokens see median TTFT drop by about 35%.

To use message threads, add the thread parameter to Messages API requests. The first request includes the full conversation and starts a thread. Each request after that includes only the new messages and the ID of the previous response. Between turns, we hold each thread in memory, where it’s encrypted and not written to disk. A thread expires 5 minutes after its last request and your client then resends the full conversation to start a new one. While each request is smaller with message threads, Claude still reads the full conversation on every turn, so token usage stays the same.

Message threads is best for active sessions where latency matters, including:

  • Long-running coding agents, where each tool result or file edit adds to the conversation.
  • Computer use agents, where screenshots stay with the thread instead of being re-uploaded on every turn.
  • Document and image-heavy workflows, where requests are made smaller.

The more context an agent carries, the more message threads can reduce time to first token.

Getting started

Message threads is available now in public beta on the native Claude Platform, and on Claude Platform on AWS, Claude in Microsoft Foundry, and on Claude Models on Google Cloud (Anthropic managed). Standard Claude token rates and existing rate limits apply. See the documentation to get started.

Explore all 41 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi