I agree that you could get to high margins, but I think the modeling holds only if you're an AI lab operating at scale with a setup tuned for your model(s). I think the most open study on this one is from the DeepSeek team: https://github.com/deepseek-ai/open-infra-index/blob/main/20...
For others, I think the picture is different. When we ran benchmarks on DeepSeek-R1 on 8x H200 SXM using vLLM, we got up to 12K total tok/s (concurrency 200, input:output ratio of 6:1). If you're spiking up 100-200K tok/s, you need a lot of GPUs for that. Then, the GPUs sit idle most of the time.
I'll read the blog post in more detail, but I don't think the following assumptions hold outside of AI labs.
* 100% utilization (no spikes, balanced usage between day/night or weekdays) * Input processing is free (~$0.001 per million tokens) * DeepSeek fits into H100 cards in a way that network isn't the bottleneck
I was modeling configurations purpose-built for running specific models in specific workloads. I was trying to figure out how much of a gross margin drag some software companies could have if they hosted their own models and served them up as APIs or as integrated copilots with their other offerings