S CostSaver
Sign in

DeepSeek V3.2

LLM

by deepseek · deepseek-deepseek-v32-20251201

Context window

164K

Max output

66K

Providers

15

Best input

$0.2088

About this model

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...

Providers & prices

Provider Input $/MTok Output $/MTok Context
G GMICloud $0.2088 $0.3096 164K
S SiliconFlow $0.259 $0.42 164K
A AtlasCloud $0.26 $0.38 164K
D DeepInfra $0.26 $0.38 164K
V Venice $0.26829 $0.39024 160K
NA Novita AI $0.269 $0.4 164K
D DeepSeek $0.269 $0.4 164K
B Baidu $0.28 $0.42 131K
D DigitalOcean $0.3 $0.96 164K
AC Alibaba Cloud (Qwen) $0.3705 $1.11 131K
F Friendli $0.5 $1.50 164K
GV Google Vertex AI $0.56 $1.68 164K
P Phala $1.00 $1.00 164K
M Mara $3.00 $4.50 33K
S SambaNova $3.00 $4.50 33K