S CostSaver
Sign in

DeepSeek V4.1 Flash (batch)

LLM

by deepseek · deepseek-deepseek-v41-flash-20260910

Context window

1.0M

Max output

131K

Providers

26

Best input

$0.04

About this model

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Providers & prices

Provider Input $/MTok Output $/MTok Context
D DekaLLM $0.04 $1.00 1.0M
M Morph $0.0975 $0.39 1.0M
O OpenInference $0.1 $0.5 1.0M
R Relace $0.1 $0.5 1.0M
SR Sail Research $0.13 $0.75 1.0M
D DeepInfra $0.14 $0.42 1.0M
D DeepSeek $0.15 $0.6 1.0M
AC Alibaba Cloud (Qwen) $0.15 $0.6 1M
S StreamLake $0.165 $0.66 1.0M
W Wafer $0.2 $0.6 1.0M
C CoreWeave $0.2 $0.65 1.0M
FA Fireworks AI $0.22 $0.66 1.0M
G GMICloud $0.225 $0.9 1.0M
K Krea $0.225 $0.9 1.0M
P Phala $0.276 $1.10 1.0M
NA Novita AI $0.285 $1.14 1.0M
N NextBit $0.3 $1.20 1.0M
A AtlasCloud $0.3 $1.20 1.0M
B BaseTen $0.3 $1.20 1.0M
M Makora $0.3 $1.20 1.0M
D DigitalOcean $0.3 $1.20 1.0M
TA Together AI $0.3 $1.20 1.0M
S SiliconFlow $0.3 $1.20 1.0M
M Modal $0.3 $1.20 1.0M
P Parasail $0.3 $1.20 1.0M
V Venice $0.375 $1.50 1M