S CostSaver
Sign in

DeepSeek V3.1

LLM

by deepseek · deepseek-deepseek-chat-v31

Context window

164K

Max output

33K

Providers

9

Best input

$0.25

About this model

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Providers & prices

Provider Input $/MTok Output $/MTok Context
D DeepInfra $0.25 $0.95 164K
D DeepSeek $0.25 $0.95 164K
NA Novita AI $0.27 $1.00 131K
S SiliconFlow $0.27 $1.00 164K
A AtlasCloud $0.3 $0.95 131K
C CoreWeave $0.55 $1.65 161K
G Google $0.6 $1.70 164K
M Mara $0.6 $1.70 131K
S SambaNova $0.65 $1.50 131K