Unlike deep-learning tasks, datacenter-grade (Tesla) GPUs don't have an advantage in mining over much cheaper consumer GPUs. As an example, a cloud-based server with dual Tesla P100 would get you 120..125 MH/s on ETH, and would cost $2,500 per month. Or, I can build a rig with consumer GPUs (1060/1070) for under $2,000 (one-time).

Interestingly, you cannot run consumer GPUs in a datacenter, as Nvidia driver terms prohibit it.

My experience in this realm:

Out of curiosity, in June or July I ran some Ethereum mining stuff on Azure's GPU instances.

The ROI was around -90% (negative 90%, to be clear: for $1 spent, I mined ~$0.10). Even with the higher price of Ethereum now, you'd probably be around that same ROI since the difficulty has also increased a fair amount.

Hmm. I didn't come to the same conclusion. Can you show your calculations?