More clarification in this article:

www.theregister.com/2025/…/deepseek_cost_train/

“But, that’s not actually what happened. Never mind the fact that $300,000 won’t buy you anywhere close to 512 H800s (those estimates are based on GPU lease rates not actual hardware costs), the researchers aren’t talking about end-to-end model training.

Instead, it focuses on the application of reinforcement learning used to imbue its existing V3 base model with “reasoning” or “thinking” capabilities.

In other words, they’d already already done about 95 percent of the work by the time they’d reached the RL phase detailed in this paper.”