DeepSeek 推理集群日处理 155 万亿 token，GPU 时收入 38 美元
精选理由
DeepSeek 把推理集群的账本公开了：日处理 155 万亿 token，GPU 时收入 38 美元，算下来毛利约 82%，这数字值得看看。
DeepSeek 公开了自建推理集群的运营数据：单集群每天处理 155 万亿 token，每个 GPU 小时产生 38 美元收入（按非高峰定价）。该集群运行 DeepInfer 推理引擎，同时支持 NVIDIA Blackwell 和华为昇腾芯片。即使按租用 B300 每 GPU 小时 7 美元的成本估算，毛利率也约为 82%。
原文 · Yuchen Jin
“A single cluster currently serves 155 trillion tokens/day, generating $38 in revenue per GPU-hour (at off-peak pricing).”
Huge flex from DeepSeek. Not only did they open-source their inference engine, but they also open-sourced their revenue numbers.
They didn't disclose which GPUs they're using here, but DeepInfer supports both NVIDIA Blackwell and Huawei Ascend.
Even assuming they're renting B300s at $7 per GPU-hour, that's ~82% gross margin.
