S CostSaver
Sign in

DeepSeek V4 Flash 0731

LLM

by deepseek · deepseek-deepseek-v4-flash-20260731

Context window

1.3M

Max output

944K

Providers

30

Best input

$0.03

About this model

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Providers & prices

Provider Input $/MTok Output $/MTok Context
D DeepSeek $0.03 $0.32 1.3M
R Relace $0.03 $0.32 1.0M
SR Sail Research $0.038 $0.55 1.0M
S StreamLake $0.0528 $0.1584 1.0M
D DeepInfra $0.06 $0.18 1.0M
W Wafer $0.08 $0.35 1.0M
I Inceptron $0.0828 $0.4138 1.0M
RA Reka AI $0.088 $0.528 262K
M Makora $0.09 $0.195 1M
D DigitalOcean $0.119 $0.238 1.0M
B BaseTen $0.13 $0.26 1.0M
C CoreWeave $0.13 $0.28 262K
P Parasail $0.14 $0.28 1.0M
TA Together AI $0.14 $0.28 1.0M
O OpenInference $0.14 $0.7 1.0M
N Nebius $0.14 $0.28 1.0M
C Cohere $0.14 $0.28 1.0M
M Morph $0.141953 $0.399625 1.0M
V Venice $0.175 $0.35 1M
AC Alibaba Cloud (Qwen) $0.176 $0.528 1M
M2 Mancer 2 $0.2 $0.6 1.0M
S SiliconFlow $0.22 $0.66 1.0M
FA Fireworks AI $0.22 $0.66 1.0M
G GMICloud $0.286 $0.858 1.0M
P Phala $0.308 $0.924 1.0M
N NextBit $0.352 $1.06 1.0M
NA Novita AI $0.4092 $1.23 1.0M
B Baidu $0.44 $1.32 1.0M
C Cloudflare $0.44 $1.32 1.3M
A AtlasCloud $0.44 $1.32 1.0M