API Vs Selfhost Skill · artvandelay bundle Decide API-vs-self-host LLM economics and fine-tuning ROI from any user context (code, PRDs, traffic logs, billing screenshots). Fetches live GPU prices from Runpod/Lambda/Modal, API prices from models.dev or vendor pages, and quality rank from lmarena.ai, then calls a deterministic local Python script for VRAM, billed-hours, and capex math. Use when the user asks "should I self-host", "API vs self-host", "fine-tune cost", "fine-tuning ROI", "what GPU do I need for <model>", "OpenAI bill too high", or pastes a billing screenshot / PRD comparing closed APIs to open-weight models.
