Skip to content
AnyRouter

DeepSeek

6 modelsModel creator

Models published by DeepSeek, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.

DeepSeek-R1
deepseek/deepseek-r1
$0.70 in
$2.50 out
64K

DeepSeek's flagship reasoning model with chain-of-thought. Strong math, coding, and complex problem solving.

Terms2
DeepSeek V3.1
deepseek/deepseek-v3.1
$0 in
$0 out
131K

DeepSeek V3.1 is a hybrid reasoning model from DeepSeek with a 131,072-token context window, strong coding and agentic tool-use performance. Served free through SambaNova Cloud's fast RDU inference and SiliconFlow.

Terms3
DeepSeek-V3
deepseek/deepseek-v3
$0 in
$0 out
128K

671B MoE general-purpose model with strong multilingual, coding, and reasoning performance.

Terms2
DeepSeek-V4-Flash
deepseek/deepseek-v4-flash
$0.04 in
$0.08 out
1M

Fast and cheap DeepSeek-V4 MoE variant via SiliconFlow free tier for high-throughput chat and coding.

Terms9
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
$0.55 in
$2.19 out
1M

DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek with a 1M-token context window on Workers AI, plus BYOK routes for other hosts.

Terms5
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
$0.15 in
$0.62 out
1M

DeepSeek V4.1 Flash is the cost-efficient sparse MoE tier of the V4.1 family (1M context, vision in, text out). Official API id is `deepseek-flash`; OpenRouter lists the same product as `deepseek/deepseek-v4.1-flash`.

Terms5