LLM

The AI Gateway LLM docs cover provider onboarding, application-facing proxies, and policy controls for Large Language Model traffic.

In This Section

• Quick Start Guide for deploying the gateway and routing traffic to an LLM provider
• LLM Provider Templates for supported provider metadata extraction and custom template management
• Guardrails for content safety, validation, and prompt protection policies
• Load Balancing for distributing traffic across models
• Prompt Management for reusable prompt shaping policies
• Semantic Caching for reducing repeated LLM calls