Skip to content
llmprice

DeepSeek V3.1 Terminus

Updated Sep 11, 2026

deepseek164k context66k max outputreleased Sep 22, 2025Open weightsReasoningTool calling
Cheapest input
$0.25
Cheapest output
$0.7
Official
output per 1M tokens
Providers
8
offering this model
Spread
1.4×
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$0.25Cheapest$0.7$0.125128k
NanoGPTopen$0.25$0.7$0.125128k
Abacusopen$0.27$1128k
Helicone$0.27$1$0.216128k
Kilo Gateway$0.27$1$0.135131k
NovitaAIopen$0.27$1$0.135131k
OpenRouteropen$0.27$1$0.135164k
Vercel AI Gatewayopen$0.27$1$0.135131k

Other deepseek models