cyberneticlibrary

Reduce LLM API costs and tokens

llm-cost-optimizerpluginsetup L217,464
alirezarezvani/claude-skills
What it does

Reduce LLM API costs and optimize token usage

Best for

Controlling LLM spend in production systems by routing between models, implementing caching, and observing token usage per feature

Inputs
  • · current API spend data
  • · model roster
  • · prompt transcript
Outputs
  • · cost reduction plan
  • · model routing strategy
  • · prompt caching config
  • · cost observability setup
Requires
  • · LLM provider APIs (Anthropic, OpenAI, etc.)
  • · token counter
  • · cost optimizer
Preconditions

Access to API billing data; at least one LLM-backed feature in production; team approval for model changes

Failure modes

Switching models introduces latency regressions users reject; prompt caching breaks for dynamic contexts; cost savings don't materialize at scale

Trust signals
  • · Covers model routing by cost/quality
  • · Prompt caching implementation included
  • · Cost observability setup
  • · v2.9.0 stable release