Skip to content
llmprice

DeepSeek-R1

Updated Sep 11, 2026

deepseek-thinking164k context41k max outputreleased Jan 20, 2025Open weightsReasoningTool calling
Cheapest input
$0.4
Cheapest output
$1.7
Official
output per 1M tokens
Providers
15
offering this model
Spread
5.1×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
NanoGPTopenCheapest$0.4Cheapest$1.7$0.2128k
D.Run (China)open$0.55$2.2131k
Alibaba (China)$0.574$2.294131k
Eden AIopen$0.7$2.4164k
Hugging Faceopen$0.7$2.564k
Kilo Gatewayopen$0.7$2.564k
OpenRouteropen$0.7$2.564k
Amazon Bedrockopen$1.35$5.4128k
Amazon Bedrockusopen$1.35$5.4128k
Merge Gatewayopen$1.35$5.4164k
Vercel AI Gatewayopen$1.35$5.4128k
IO.NETopen$2$8.75$1$4128k
Abacusopen$3$7128k
iFlowfreefreefree128k

Other deepseek-thinking models