Understand this story
Anthropic has opened the public beta of the message threads feature on the Messages API. According to Claude Devs, the API caches conversations on the server side, so developers only need to send the new message and the ID of the previous message, without resending the full conversation. The feature has already been integrated into Claude Code; on requests of 500K to 1M tokens, median time to first token is reduced by about 35%, and in long conversations the median request size drops from about 800 KB to 1.8 KB. To use it, a thread parameter and a beta header must be added to the request; the feature is available on Claude Platform, Claude Platform on AWS, Claude in Microsoft Foundry, and Claude on Google Cloud, and is billed at standard token prices. The Claude Blog separately states that threads expire 5 minutes after the last request, are stored encrypted in memory during that time and not written to disk, and token usage is unchanged.
AI-generated from public reports
Latest update · Discussion
Baoyu joined this discussionDevelopments
1 confirmed developments
Anthropic opens public beta of message threads feature in Messages API
Source:Claude Devs
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 3
BaoyuRelated discussion
Baoyu joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Unite.AI
Anthropic Launches Message Threads Beta for Long-Running Agents
On November 2, 2026, Anthropic launched the public Beta of message threads. After a Messages API application sends the full conversation for the first time, subsequent requests only need to send new messages. Anthropic says that with the feature enabled by default for most Claude Code users, median time to first token for requests of 500,000 to 1 million tokens dropped by about 35%. Threads expire five minutes after the last request, content is stored only in memory and retained for at most one hour, zero data retention and HIPAA scenarios are not supported, and applications still need to save the full conversation themselves for replay.
Unite.AIRelated discussion
Unite.AI joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Claude DevsFirst-partySelected
Anthropic Opens Public Beta of Message Threads in the Messages API
Anthropic has opened the public beta of message threads on the Messages API. The API caches conversations on the server side, so developers only need to send the new message and the previous message ID, without resending the full conversation. The feature has been integrated into Claude Code; on requests of 500K to 1M tokens, median time to first token dropped by about 35%, and in long conversations the median request size fell from about 800 KB to 1.8 KB. To use it, add the thread parameter and beta header to requests. The feature is available on Claude Platform, Claude Platform on AWS, Claude in Microsoft Foundry, and Claude on Google Cloud, and is billed at standard token prices.
Claude DevsFirst-party
Anthropic Opens Message Threads Beta in the Messages API
Anthropic has launched the message threads beta on its Messages API. The API caches conversations server-side, so subsequent requests only need to send the new message and the previous message ID, allowing Claude to start responding faster. The company says the feature is already integrated in Claude Code, with median time to first token for 500K to 1M token requests reduced by about 35%, and median request size for long conversations dropping from about 800 KB to 1.8 KB. To use it, add the thread parameter and beta header to requests. The feature is available on Claude Platform, Claude Platform on AWS, Claude in Microsoft Foundry, and Claude on Google Cloud, and is billed at standard token prices.
Nov 2
Claude BlogFirst-party
Anthropic Launches Message Threads in Public Beta on the Messages API
Anthropic has launched the public beta of message threads for the Messages API on the Claude Platform; agents now only need to send newly added content each turn rather than resending the full conversation history. For requests of 500k to 1M tokens, median time to first token (TTFT) drops by about 35%, and the feature is enabled by default for most Claude Code users. To use it, add the thread parameter to the request, send the full conversation and open the thread in the first turn, then include only the new message and the previous response ID in subsequent turns; threads expire 5 minutes after the last request, are stored encrypted in memory during that period and not written to disk, and token usage remains unchanged.