Version
InferenceGateway Custom Resource
On this page
Unified OpenAI-compatible endpoint on the control plane cluster.
Concept guide: Set Up the Gateway →
#Metadata
#Example
Manifest
apiVersion: modelplane.ai/v1alpha1
kind: InferenceGateway
metadata:
name: default
spec:
backend: Traefik
traefik:
version: "40.2.0"
loadBalancer: MetalLB
metallb:
addressPool: "172.18.255.200-172.18.255.250"
#Spec
Gateway implementation.
Traefik Proxy configuration. Required when backend is Traefik.
Load balancer implementation for the gateway Service. Omit for cloud environments where a native LB controller is available.
MetalLB configuration. Required when loadBalancer is MetalLB. Use for kind or bare-metal clusters.
IP address range for the MetalLB pool (e.g. “172.18.255.200-172.18.255.250”). Must be within the cluster’s network CIDR.
Traefik Helm chart version.
#Status
External address of the control plane gateway. Backend-agnostic — works for any routing implementation.