LLM Auto-Switch System

What problem does it solve?

This Skill addresses the high cost of using advanced Large Language Models (LLMs) by automatically switching to more cost-effective models based on task complexity.

Core Features & Use Cases

• Dynamic Model Routing: Selects the optimal LLM (Opus, Sonnet, Haiku, Ollama, OpenRouter) based on estimated task difficulty.
• Cost Reduction: Aims to reduce monthly LLM expenses by 47-58%.
• Budget Management: Implements a budget guardrail with automatic fallback to free models when limits are exceeded.
• LiteLLM Integration: Utilizes LiteLLM with Docker Compose for a robust and scalable setup.
• Use Case: When processing a large batch of customer support tickets, this skill can route simple inquiries to a free local model while complex ones go to a premium API, ensuring cost efficiency without sacrificing quality.

Quick Start

Execute the llm-auto-switch skill to set up the model routing system.