Anthropic adds message threads to the Claude API, so long agent loops send only new messages
Anthropic released message threads in public beta for the Claude Messages API, letting a long conversation stay on Anthropic's servers briefly so each later request carries only the new messages and the previous response ID.
What happened
- The Claude Platform release notes for November 2, 2026 list message threads as a beta, turned on with the message-threads-2026-08-12 beta header.
- The first request carries the whole conversation and tool definitions; each later request carries only the new messages plus the previous response's ID, and the API rebuilds the conversation before calling the model.
- A thread expires 5 minutes after its last request and is deleted no more than 1 hour after its last use; if it has expired, the client resends the full conversation.
- Anthropic says threads are on by default for most Claude Code users, and that median time to first token on 500k to 1M token requests dropped by about 35%.
- Token prices and rate limits are unchanged, because Claude still reads the whole conversation on every turn; the docs say threads are not eligible for zero data retention.
Why it matters: Developers building long-running coding, computer-use or document agents on Claude can cut the wait before each reply without changing prompts. It saves time, not money, and teams with zero-data-retention requirements can't use it.
Sources
- Claude Platform release notes platform.claude.com
- Claude docs: Message threads platform.claude.com
- Anthropic: Make long-running agents faster with message threads claude.com
Checked November 3, 2026 against the sources above. Claims about performance or benchmarks are the company's own unless stated otherwise.