Features

Detailed documentation for each LLM Gateway capability - Routing, Token Saving, Guardian Agent, Guardrails, Prompt Store, Identity Aware, and more.

Request Routing

Multi-provider load balancing and failover behind a single API key.

Reduce token usage by compressing input content automatically.

Guide model behavior with gateway-side policy checks for dependency safety and task adherence.

Detect and act on sensitive data and adversarial inputs.

Define your own detection categories with examples.

Control request rates, token budgets, and key expiry.

Manage and version system prompts centrally.

Test your guardrails configuration against adversarial prompts.

Authenticate and track users behind each API key.

Scan content directly from your application code - no LLM proxy required.

Group related requests together so logs and analytics can be viewed at the conversation level.

Connect Microsoft Copilot Studio external threat detection to QuilrAI guardrails.