DeepSeek V3.2

DeepSeek · deepseek/deepseek-v3.2

← Back to leaderboard

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...

open weightstexttext->text

Context

Max context: 128000
Max output: 64000

Pricing

Input / 1M: 0.23
Output / 1M: 0.34
Blend / 1M: 0.29

Quality

Quality index:

Provider

Provider: DeepSeek
Moderated: no