Skip to content
llmprice

DeepSeek V3.2 Thinking

Updated Sep 11, 2026

deepseek163k context128k max outputreleased Dec 1, 2025Open weightsReasoningTool calling
Cheapest input
$0.28
Cheapest output
$0.42
Official
output per 1M tokens
Providers
3
offering this model
Spread
4.4×
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$0.28Cheapest$0.42$0.14163k
302.AI$0.29$0.43128k
Vercel AI Gateway$0.62$1.85128k

Other deepseek models