Azure & Cloud
November 4, 2026Claude message threads in Foundry: faster, not cheaper
Claude message threads went into public beta on 2 November 2026, including on Microsoft Foundry: send the conversation once, then only new messages and an id, for about 35% lower time to first token on 500K to 1M token requests. Token charges and rate limits do not change, so caching remains the cost lever. The thread is a server-side copy of your conversation, held in memory for up to an hour and outside ZDR, which EU teams need to document.
Claude
message threads
Microsoft Foundry
prompt caching
Azure OpenAI
Responses API
Opus 5.5
zero data retention
GDPR
molnpolicy
AI agents
latency
By Falak Mahmood