Anthropic announced message threads, a new feature available now in public beta for its Messages API and already enabled by default for “most” Claude Code users, according to an article published by Anthropic on Monday. The feature aims to speed up long-running Claude Code sessions by reducing the amount of conversation data repeatedly sent to its API. Anthropic says the feature has reduced median time to first token (TTFT) by approximately 35% for Claude Code requests containing between 500,000 and 1 million tokens. Because it is part of the Messages API, the feature also extends beyond Claude Code to developers building their own AI agents, particularly those handling lengthy conversations, repeated tool calls, and large amounts of data. Traditionally, every request to Claude included the entire conversation history, requiring all messages and tool calls to be transmitted again; message threads instead allows Anthropic to temporarily retain conversation history on its servers, so the first request still sends the complete conversation, including any system prompts and tool definitions, while subsequent requests need only contain new messages and a reference to the previous response. Anthropic reconstructs the full conversation on its servers before passing it to Claude. Claude still processes the entire conversation on every turn, so token usage stays the same.