← LLM API pricing

DeepSeek V4.1 Flash

DeepSeek

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...

In
$0.04
Out
$0.50
Blended
$0.16
Where to buy this model
32 access routes
RouteInOutBlendedvs
● Morph cheapestfp8$0.04$0.32$0.11-
● Decart fp4$0.09$0.18$0.11+0%
● Sail Research fp4$0.09$0.25$0.13+18%
● OpenInference fp4$0.04$0.50$0.15+36%
● Relace fp4$0.04$0.50$0.15+36%
● Wafer mxfp4$0.04$0.50$0.16+45%
DeepInfra fp8$0.11$0.34$0.17+55%
● InferenceNet fp8$0.10$0.60$0.23+109%
● AtlasCloud fp8$0.14$0.54$0.24+118%
● StreamLake fp8$0.15$0.59$0.26+136%
● CoreWeave fp8$0.13$0.65$0.26+136%
● Reka $0.10$0.84$0.29+164%
● Mancer 2 fp8$0.15$0.75$0.30+173%
GMICloud fp8$0.18$0.72$0.32+191%
Novita fp8$0.20$0.78$0.34+209%
Fireworks $0.21$0.84$0.37+236%
● Phala $0.21$0.84$0.37+236%
DigitalOcean $0.23$0.90$0.39+255%
● PrimeIntellect $0.16$1.20$0.42+282%
● Makora fp8$0.26$1.17$0.49+345%
● Crusoe fp8$0.29$1.20$0.52+373%
Google $0.30$1.20$0.52+373%
Nebius fp8$0.30$1.20$0.52+373%
● Cohere $0.30$1.20$0.52+373%
● Baidu fp8$0.30$1.20$0.52+373%
BaseTen $0.30$1.20$0.52+373%
Together $0.30$1.20$0.52+373%
● SiliconFlow fp8$0.30$1.20$0.52+373%
● Modal $0.30$1.20$0.52+373%
Parasail fp8$0.30$1.20$0.52+373%
● Venice fp8$0.30$1.20$0.52+373%
● Alibaba $0.33$1.32$0.58+427%

● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.

Ctx
1.048576M
max output
944K
cache read /1M
$0.01
Family
deepseek
Modalities
text · image
Features
json · reasoning · tools

Live pricing, updated 2026-11-03.

DeepSeek models at a similar price
ModelInOutCtx
DeepSeek V4 Flash 0423$0.091$0.1821.048576M
DeepSeek V4.1 Flash · this model$0.045$0.51.048576M
DeepSeek V3.2$0.26$0.38164K
DeepSeek V3.2 Exp$0.27$0.41164K
DeepSeek V4 Flash Vision Exp$0.216$0.6471.048576M
DeepSeek V3.1$0.25$0.95164K

Concepts on this page