Anthropic opens message threads beta to speed long-running agents
Anthropic's Claude Platform now offers message threads in public beta, so agents no longer resend the full conversation history on every turn, cutting latency.
By GennnAi··1 min read
ClaudeClaude PlatformClaude CodeMessages APIAWSMicrosoft FoundryGoogle CloudOutilsInfrastructureFlash
For requests of 500k to 1M tokens, median time to first token drops about 35%, and the feature is on by default for most Claude Code users. Developers add a thread parameter to Messages API requests; a thread expires five minutes after its last request. Token usage stays the same, and standard rates and rate limits apply. It is also available on Claude Platform on AWS, Microsoft Foundry and Google Cloud.
Source: Anthropic, published on November 2, 2026.