S CostSaver
Sign in

DeepSeek V4 Flash 0423

LLM

by deepseek · deepseek-deepseek-v4-flash-20260423

Context window

1.0M

Max output

384K

Providers

17

Best input

$0.03

About this model

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Providers & prices

Provider Input $/MTok Output $/MTok Context
R Relace $0.03 $0.64 1.0M
B Baidu $0.06692 $0.13384 1.0M
D DeepSeek $0.06706 $0.13412 1.0M
S StreamLake $0.06706 $0.13412 1.0M
D DeepInfra $0.09 $0.18 1.0M
G GMICloud $0.091 $0.182 1.0M
V Venice $0.0966 $0.1925 1M
D DigitalOcean $0.098 $0.196 1.0M
S SiliconFlow $0.13 $0.28 1.0M
AC Alibaba Cloud (Qwen) $0.134 $0.268 1M
O OpenInference $0.14 $0.7 1.0M
A AtlasCloud $0.14 $0.28 1.0M
NA Novita AI $0.14 $0.28 1.0M
P Parasail $0.14 $0.28 1.0M
N NextBit $0.15 $0.3 1.0M
M2 Mancer 2 $0.19 $0.5 1.0M
MA Microsoft Azure $0.21 $0.56 1.0M