I built an LLM router that picks a different model per article type

A developer built an LLM router that selects a different model per article type for a network of niche content sites. The pipeline uses a router to pick models for news, reviews, and tutorials, with daily re-scoring and auto-regeneration of failures. The project, built on Next.js 16 and MDX, aims for a $30k/mo run-rate in 24 months through guest-link sales.

I've been quietly running a small network of niche content sites for a few weeks. Two are live on real domains: The niche isn't the interesting part. The pipeline is. Instead of one model for everything, a router picks per article type: Every draft, before it ships, passes through: A daily job re-scores everything published in the last 24h and auto-regenerates the failures. The whole thing is Next.js 16 + MDX, one git repo per site. The honest target: a $30k/mo run-rate in ~24 months across 30 mature sites, monetized through guest-link sales, not ads. Slow on purpose. Happy to go deeper on the router logic or the QA scoring if anyone's interested.