how can deepseek be so cheap\* yet so effective? \*pricing: MODEL deepseek-chat ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		niteshpant 10 days ago \| parent \| context \| favorite \| on: DeepSeek-v3.1 how can deepseek be so cheap* yet so effective? *pricing: MODEL deepseek-chat deepseek-reasoner 1M INPUT TOKENS (CACHE HIT) $0.07 1M INPUT TOKENS (CACHE MISS) $0.56 1M OUTPUT TOKENS $1.68

Alifatisk 10 days ago [–]

I think it's because of a combination between the MoE model architecture and the inference done in large batches and run in parallel

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact