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...
Rank
#28
Up 4% week over week
Tokens
403.2B
2026-08-14
Requests
55.1M
55,066,374
Tool calls
-
Input / M
$0.27
Output / M
$0.40
Cache / M
$0.13
Context
164K
163,840 tokens