Models·DeepSeek

DeepSeek V3.1

deepseek/deepseek-chat-v3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

$0.25Input, per million tokens
$0.95Output, per million tokens
164KContext window
33KLongest answer

164K tokens of context — about 122,880 words, on a scale that ends at 2M.

What it can do

  • Reasoning
  • Tool use
  • Open weights
  • Takes text
  • Gives text

Released 21 Aug 2025 · checked 3 Oct 2026.

On these boards

More from DeepSeek