The problem with the rent-a-server approach over buying AWS is that, in many cases, your engineering team will need to implement a ton of APIs, tooling, monitoring, alerting, etc. to get the same quality of service that you get from a public cloud vendor "for free." Which is great for us engineers since it's interesting problems that need solving, but not so much for the PMs that need to justify that spend.

Also, when your web service scales to millions of requests per second from millions of requests a month or week or whatever, having elastic compute that can scale with that is a blessing. Because nobody wants to wait for page loads: