Skill UI

Analyze prompt structure to maximize LLM cache reuse, then measure input cost and latency. Covers stable prefixes, user/workspace boundaries, provider-specific cache counters and a cost comparison calculator for OpenAI, Claude and Gemini.

Calculate the cost per million tokens for running AI models locally on your own hardware like Ollama or llama.cpp. It factors in electricity prices, hardware costs, power consumption, and generation speed to determine the break-even point against hosted API models. Useful for deciding whether to deploy models locally or use cloud services based on actual usage and financial constraints.