The LLM gateway's guides are under construction and land with the feature. They will cover putting one endpoint in front of several model providers, with failover, token budgets and guardrails. Until then, start at the LLM gateway docs, or see AI inference for routing to self-hosted model servers.
LLM
Guides for the LLM gateway: one endpoint in front of several model providers, with failover, token budgets and guardrails.