Selects optimal model endpoint based on query complexity, budget, and latency tolerance
Selects optimal model endpoint based on query complexity, budget, and latency tolerance
Lightweight Local AI Proxy & Real-Time Cost/Debugging Dashboard for OpenAI, Anthropic & Ollama
A Kubernetes cost analyzer that maps every pod's resource requests to the node it runs on, looks up that node's hourly cloud price, and ranks pods by how much money they're wasting.
Claude Opus 5 tariff-cost planner for heavy API users — estimate monthly premiums before you burn credits.
SkillFM Beacon MCP: AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits.
Intelligent task classifier and AI model router with cost estimation and capability matching in pure PHP
LLM Prompt Cache Invalidation & Cost Leak Detector. Pinpoint exact cache break points and stop silent API dollar leaks.
To associate your repository with the cost-optimizer topic, visit your repo's landing page and select "manage topics."