Chat with DeepSeek V4.1 Flash.

DeepSeek’s newest quick model, and the first on a new design of theirs. It wakes only a small part of itself for each word, so it stays fast and cheap, and it reads pictures as well as text.

Start chatting with DeepSeek V4.1 Flash now — free, no account

At a glance

  • Maker: DeepSeek
  • Active parameters: 763B
  • Context window: 1M
  • Size: Very large
  • Memory: Handles very long documents
  • Good at: Fast, cheap work on long inputs
  • Supports: tools, images, zero data retention

Model availability changes as upstream capacity comes and goes — the picker on the chat page shows what is ready right now.

← All models on UsingOpen