DeepSeek V3.2
deepseek/deepseek-v3.2DeepSeek-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
- DeepSeek Flash Latest$0.015 in
- DeepSeek Pro Latest$0.13 in
- DeepSeek V4.1 Flash$0.30 in
- DeepSeek V4.1 Flash (batch)$0.11 in
- DeepSeek V4 Flash Vision Exp$0.22 in
- DeepSeek V4 Pro 0813$0.66 in
- DeepSeek V4 Flash Latest$0.009 in
- DeepSeek V4 Flash 0731$0.011 in
- DeepSeek V4 Flash 0423$0.028 in
- DeepSeek V4 Pro 0423$0.21 in
- DeepSeek V3.2 Exp$0.27 in
- DeepSeek V3.1 Terminus$0.27 in
- DeepSeek V3.1$0.25 in
- R1 0528$0.50 in
- DeepSeek V3 0324$0.29 in
- R1$0.70 in
- DeepSeek V3$0.26 in