← LLM API pricing

DeepSeek V3.1

DeepSeek

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...

In
$0.25
Out
$0.95
Blended
$0.43
Where to buy this model
5 access routes
RouteInOutBlendedvs
DeepInfra cheapestfp4$0.25$0.95$0.43-
● SiliconFlow fp8$0.27$1.00$0.45+5%
● CoreWeave fp8$0.55$1.65$0.83+93%
SambaNova fp8$0.65$1.50$0.86+100%
● Mara $0.60$1.70$0.88+105%

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

Ctx
164K
max output
147K
cache read /1M
$0.13
Family
deepseek
Modalities
text
Features
json · reasoning · tools

Live pricing, updated 2026-11-03.

DeepSeek models at a similar price
ModelInOutCtx
DeepSeek V3.2 Exp$0.27$0.41164K
DeepSeek V4 Flash Vision Exp$0.216$0.6471.048576M
DeepSeek V3.1 · this model$0.25$0.95164K
DeepSeek V3$0.257$1.03164K
DeepSeek V3.1 Terminus$0.27$1164K
DeepSeek V3 0324$0.29$1.14164K

Concepts on this page