Models·DeepSeek

DeepSeek V3.2

deepseek/deepseek-v3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

$0.28Input, per million tokens
$0.42Output, per million tokens
164KContext window
66KLongest 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 1 Dec 2025 · checked 3 Oct 2026.

On these boards

More from DeepSeek