Blog.
Analysis and opinion on models, inference, and the economics behind them.
October 28, 2026Is hosting an open-source inference engine profitable?Is hosting an open-source inference engine profitable? Public data on DeepSeek V4.1 Flash: H200 never breaks even, B300 breaks even at 35% utilization.
Yingjun WuOctober 25, 2026The case for specialized intelligenceWhy we think a large share of AI's value sits in decisions, extraction and judging inside applications, and what it takes in models, evaluation and compute to serve that at scale.