Hey Product Hunt 👋 I built Decisor after repeatedly running into the same problem: LLM costs getting out of control. Most apps don’t need GPT-4 for every single request — but manually deciding which model to use quickly becomes complex and error-prone. Decisor is a smart LLM router that automatically routes each request to the most cost-efficient model while maintaining quality. In real-world usage, this can reduce inference costs by up to 90%. The approach evolved a lot while building it: from simple rule-based routing to smarter decision logic based on task complexity, cost, and performance. The goal was to make cost savings feel effortless — just plug it in and let it decide. I’d love to hear your thoughts, feedback, or how you’re currently managing LLM costs in your own products 🙌

Decisor

Smart LLM routing to cut AI costs by up to 90%

Smart LLM routing to cut AI costs by up to 90%