I built a router that automatically sends your AI tasks to the most appropriate model to handle them at low cost - 9,200 tasks in, $21 saved at $0.14 actual cost

The observation that started this: most of what people use AI for every day - summarising, drafting, classifying, extracting etc doesn't actually require a frontier model. Any competent 8-70B model handles those just as well. But most people run everything through Claude or ChatGPT out of habit. I built Followloop (followloop.app) to solve this automatically. It classifies each task by complexity and routes it: - Simple tasks → Cerebras Llama (2000 TPS, 1M tokens/day free), Groq, Gemini Flash