LLM Cost Optimization

Use when an application that calls an LLM API costs too much, needs a cost forecast, or is about to ship at scale — "the bill is too high", "make this cheaper", "should we route to a smaller model". Profiles spend per completed task from usage logs, then applies levers in order: prompt caching, input-token hygiene, agent-loop hygiene, output control, and batch APIs before effort, budget, and model-routing tradeoffs validated on an eval. Provider-agnostic, with Anthropic specifics.

mouadja02 Updated 13 repo stars

File contents

mouadja02/skills commit f38aa1e988

Frequently asked questions

npx get-skill add mouadja02/llm-cost-optimization