DeepInfer bersumber terbuka DeepSeek, mesin di balik API-nya.
Its receipt: $38 of revenue per GPU-hour (off-peak). In 2025 the same math gave ~$13 on H800s. The catch: 64 + 64 Blackwell-class GPUs, and no cache store in the repo.
DeepSeek DeepInfer adalah mesin di balik API DeepSeek, bersumber terbuka pada 20 Oktober 2026.
DeepSeek says one GPU earns $38/hour off-peak. The tricks: split prefill/decode, decode across 64 GPUs, 96% cache hits (reported). The catch: the cache isn't in the repo.
HY4 vs DeepSeek V4.1 Flash 1017
My first thoughts. HY4 is a fucking expensive overthinker. Painfully slow, thinks way too much, and the final quality is only slightly better than DeepSeek. and guess what? this single test cost me $31.41 via AIHubMix 💀 I'd pick DeepSeek
Sudah sampai ujung arsip
Semua deepseek