LLM Gateway and Routing

Purpose: Stop calling LLM provider SDKs directly from app code. Put a gateway in front so you can swap models, cap cost, and survive provider outages.

When to Use This Skill

• Multiple apps or teams calling LLMs in your org
• Multiple providers in play (OpenAI + Anthropic + Azure + open-weights)
• Need centralized cost, rate-limit, audit, and key management
• Want semantic caching to cut spend
• Need provider failover for SLO

What a Gateway Buys You