How're you deploying LLMs in production now-a-days? What's the best and most affordable way? [D]

I've been developing an AI product using LLM APIs (from OpenRouter) but want to deploy an open-source LLM in my own Prod env. which I can control. Few reasons behind this are: - I wanna own the complete stack around my product. - Second I wanna fine-tune the model around my usecase. So, what's the m