Official2026-06-11

DeepSeek Rate Limits Use Account Concurrency and user_id

Checked on June 11, 2026: DeepSeek's official docs now give a cleaner production picture for V4 traffic management, with 500 Pro concurrency, 2500 Flash concurrency, explicit `user_id` isolation rules, and request keep-alive handling.

What we verified on June 11, 2026

  • DeepSeek's official Rate Limit & Isolation page sets account-level concurrency at 500 for deepseek-v4-pro and 2500 for deepseek-v4-flash.
  • The same official page now explains what user_id does: content-safety isolation, KV-cache isolation, and scheduling isolation under one account.
  • DeepSeek also documents protocol-specific user_id placement: extra_body.user_id for OpenAI-format calls and metadata.user_id for Anthropic-format calls.
  • The same page documents the request keep-alive behavior: non-streaming responses can emit empty lines, streaming responses can emit SSE keep-alive comments, and the server closes the connection if inference has not started after 10 minutes.
  • DeepSeek's English homepage still points its public social anchor to @deepseek_ai, which remains the safest official X confirmation even though the X page itself is not safely crawlable here.

Sources