Short answer: the best way to reduce LLM cost for a product catalog is to measure cost per accepted record, then route each job by difficulty. Count prompt tokens before the call, use a small model for the easy summarize/classify/extract-JSON cases, reserve a stronger model for exceptions, and b...
Source: [Dev.to](https://dev.to/mordecainilsson7582/reduce-llm-cost-for-catalog-compare-small-models-to-summarize-classify-and-extract-json-35e7)