LLM Gateway
Point your apps at one OpenAI-compatible endpoint. Every request gets guardrails, routing, limits and cost tracking, whichever provider serves it.
In the console: Settings > AI Gateway > LLM Gateway

Get going
Send your first requestCreate an app, copy its key, call the gatewayConnect a providerOpenAI, Anthropic, Azure, Bedrock, Vertex, OCIAny-to-any formatsCompare client formats and provider support, and see how requests are convertedTurn on guardrailsBlock or redact sensitive data and attacksAutomate apps and keysManage apps, keys and configuration with the Management API
Everything in LLM Gateway
67 pages
Apps and providers10
Protect11
Cost and traffic7
API reference21
- Any-to-any formats
- Inference API
- Log export API
- Management API
- Apps and credentials API
- Providers and configuration API
- Prompts API
- Budgets API
- Smart groups API
- Agents API
- Routing and failover API
- Rate limits API
- Access and features API
- Incidents API
- Hooks API
- Usage API
- Monitoring API
- Users API
- Self-service API
- Policy API (QuilrQL)
- Endpoint families