llm11

DeepSeek models

llm11 can call 14 DeepSeek models through one API, with Jev, TypeSafe AI's System One model, deciding which one answers each request. Blended prices run from $0.093 to $1.41 per million tokens. The newest is DeepSeek V4.1 Flash, released 2026-09-10.

DeepSeek models with live prices
ModelInput / 1MOutput / 1MContext
DeepSeek V4.1 Flash$0.300$1.201.05M
DeepSeek V4 Flash Vision Exp$0.216$0.6471.05M
DeepSeek V4 Pro 0813$0.480$4.201.05M
DeepSeek V4 Flash 0731$0.018$0.3201.31M
DeepSeek V4 Flash 0423$0.140$0.2801.05M
DeepSeek V4 Pro 0423$0.955$1.911.05M
DeepSeek V3.2$0.280$0.420164K
DeepSeek V3.2 Exp$0.270$0.410164K
DeepSeek V3.1 Terminus$0.300$1.00164K
DeepSeek V3.1$0.250$0.950164K
R1 0528$0.500$2.15164K
DeepSeek V3 0324$0.290$1.14164K
R1$0.700$2.5064K
DeepSeek V3$0.257$1.03164K

Read from the live catalogue and refreshed daily. Prices are per million tokens.

Questions

Which DeepSeek models can I call through llm11?
14 today, listed with live prices on this page. The list follows the upstream catalogue, so a new DeepSeek model appears here without anyone editing the page.
What is the cheapest and the most expensive DeepSeek model?
By blended price, weighting three parts input to one part output: DeepSeek V4 Flash 0731 is cheapest at $0.093 per million tokens, and DeepSeek V4 Pro 0813 is the most expensive at $1.41.
What is the newest DeepSeek model?
DeepSeek V4.1 Flash, released 2026-09-10. Call it with model set to deepseek/deepseek-v4.1-flash.

Other labs