Anthropic launches message threads beta for lower-latency long agent loops

Anthropic's Messages API can now send smaller requests and get lower time-to-first-token on long conversations and agent loops via message threads, in beta with the message-threads-2026-08-12 header. The API keeps the conversation server-side so later requests send only new messages; a thread expires 5 minutes after its last request and is deleted within 1 hour of last use. Available on the Claude API, Claude Platform on AWS, Claude Models on Google Cloud, and Claude in Microsoft Foundry.

Significance 2: An incremental developer-platform latency/cost improvement for agentic workloads; useful but does not move a tracked benchmark or score.

Sources

• primary Claude Platform release notes retrieved 2026-11-04

← Back to feed