From the source
Anthropic has put message threads into public beta on the Claude Platform, letting agents send only new messages instead of resending the whole conversation each turn.
- A coding agent can make hundreds of requests in one session, and once a conversation reaches hundreds of thousands of tokens, resending all of it delays Claude's first response.
- With message threads on by default for most Claude Code users, requests carrying 500k to 1M tokens see median time to first token fall by about 35%, Anthropic says.
- Developers add the thread parameter to Messages API requests: the first request carries the full conversation and opens a thread, and later requests carry only new messages plus the previous response ID.
- Anthropic holds each thread in memory, encrypted and not written to disk, and a thread expires 5 minutes after its last request, at which point the client resends the full conversation.
- Token usage stays the same because Claude still reads the full conversation on every turn, and the feature is available on the native Claude Platform, Claude Platform on AWS, Claude in
Microsoft Foundry and Claude Models on
Google Cloud.


