DeepSeek Open-Sources Inference Engine, Reveals 155T Daily Tokens
DeepSeek has open-sourced its inference engine, DeepInfer, and disclosed operational metrics showing a single cluster processes 155 trillion tokens daily at $38 revenue per GPU-hour. The engine supports both NVIDIA Blackwell and Huawei Ascend chips, implying an estimated gross margin of ~82% based on B300 rental costs.
Full Report
Yuchen Jin (@Yuchenj_UW) · 2026-10-21 04
My entire job at Databricks:
Step 1: Buy a sh*tload of GPUs Step 2: Read DeepSeek blogs Step 3: Profit
↳ 引用 @Yuchenj_UW (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.