←back to thread

DeepSeek-v3.1

(api-docs.deepseek.com)
776 points wertyk | 1 comments | 21 Aug 25 19:06 UTC | HN request time: 0.201s | source
Show context
niteshpant ◴[22 Aug 25 15:21 UTC] No.44985717[source]▶
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

replies(1): >>44985836 #
1. Alifatisk ◴[22 Aug 25 15:31 UTC] No.44985836[source]▶
I think it's because of a combination between the MoE model architecture and the inference done in large batches and run in parallel