Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

DeepSeek API

Open in consoleI need inference

Pricing

ModelReleasedContextInput / 1MOutput / 1MProvidersWeights
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017October 17, 20261.05M$0.09Sail Research$0.30Sail Research2Open
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashSeptember 10, 20261.05M$0.09Sail Research$0.30Sail Research7Open
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expAugust 21, 20261.05M$0.2156DeepInfra$0.6468DeepInfra1Open
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813August 13, 20261.05M$0.92Sail Research$2.60DeepInfra4Open
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731July 31, 20261.05M$0.06DeepInfra$0.18DeepInfra4Open
DeepSeek V4 Flashdeepseek/deepseek-v4-flashApril 24, 20261M$0.23Inference.net$0.62Inference.net1Open
DeepSeek V4 Prodeepseek/deepseek-v4-proApril 24, 20261.05M$1.30DeepInfra$2.60DeepInfra3Open

Lowest listed price, USD per 1M tokens, as of October 27, 2026.

FAQ

Which DeepSeek models can I use through RouterPlus?

DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash, DeepSeek V4 Flash Vision Exp, DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, DeepSeek V4 Flash and DeepSeek V4 Pro. Each one uses its catalog ID, such as "deepseek/deepseek-v4.1-flash-1017", with the OpenAI-compatible endpoint at https://api.routerplus.com/v1.

What is the cheapest DeepSeek model on RouterPlus?

DeepSeek V4 Flash 0731, at $0.06 per million input tokens and $0.18 per million output tokens on DeepInfra. Prices as of October 27, 2026.

Which DeepSeek model has the most providers?

DeepSeek V4.1 Flash, served by 7 providers: Morph, DeepInfra, Nebius, Novita AI, Inference.net, RunInfra and Sail Research.

What is the newest DeepSeek model?

DeepSeek V4.1 Flash 1017, released October 17, 2026, is the newest DeepSeek model in the RouterPlus catalog.

Run DeepSeek in production

Open in consoleI need inference