DeepSeek 宣布开源自研推理框架 DeepInfer，用于支撑 DeepSeek-V4.1-Flash 的大规模高吞吐低延迟推理服务。作者补充知乎文章细节：单集群服务吞吐 155 万亿 token/天，整体收入 $38 per card per hour（按错峰价格计）；作者据此估算 GPU 成本约 $5-10 每小时，称 DeepSeek 在其定价下推理服务毛利约 80%。
原文引用知乎长文给出单集群吞吐和每卡收入数字，可据此推算 DeepSeek 自述的推理服务毛利空间。
deepseek posted way more alpha on their zhihu page, if you only read twitter you are reading the laowai approved stuff
"Based on this framework, we have implemented a high-throughput, low-latency large-scale inference service for DeepSeek V4.1 Flash. Currently, the service throughput of a single cluster is 155 trillion tokens/day, and the overall revenue is $38 per card per hour (based on off-peak prices)."
it costs roughtly $5-10 per gpu hour so depseek is claiming 80% serving margin at THEIR prices lololololol
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 http://github.com/deepseek-ai/DeepInfer 1/4在 X 查看被引用的帖子
来源：swyx · x.com