They certainly are not providing these services at less than electricity costs. So if you are spending $20 a month on it, they are spending less than that on electricity. It's very low compared to any person in the first world's energy spend.
The math just doesn't work. They're hemorrhaging money as far as I can tell (not counting the Azure computing deal).
We can only guess, but my guess is that inference is still a good chunk of their costs. That's why they're trying to get the mini/turbo models into a usable state.
Even then, training is still an expense. And it's not like you can train and forget. Even if your model is already trained you still need to incorporate new knowledge over time.
There is about zero chance OpenAI are running their service at a 70% negative gross margin.