The LLM Router Pattern in 2026: Model Routing, Fallbacks, and Cost Control That Actually Works

The bill that broke me last year was the second month of a feature I was proud of. The product was working. Users were happy. The model was Claude Opus on every request, including the ones where a junior model would have done the job in a third of the time for a tenth of the cost. I knew the bill was going to be high. I did not know it was going to be that high. I spent a weekend rewiring the feature to pick a model per request based on the actual difficulty of the work, and the bill the next