plano/demos/llm_routing/model_routing_service/plano-deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: plano
  labels:
    app: plano
spec:
  replicas: 1
  selector:
    matchLabels:
      app: plano
  template:
    metadata:
      labels:
        app: plano
    spec:
      containers:
        - name: plano
          image: katanemo/plano:0.4.12
          ports:
            - containerPort: 12000  # LLM gateway (chat completions, model routing)
              name: llm-gateway
          envFrom:
            - secretRef:
                name: plano-secrets
          env:
            - name: LOG_LEVEL
              value: "info"
          volumeMounts:
            - name: plano-config
              mountPath: /app/plano_config.yaml
              subPath: plano_config.yaml
              readOnly: true
          readinessProbe:
            httpGet:
              path: /healthz
              port: 12000
            initialDelaySeconds: 5
            periodSeconds: 10
          livenessProbe:
            httpGet:
              path: /healthz
              port: 12000
            initialDelaySeconds: 10
            periodSeconds: 30
          resources:
            requests:
              memory: "256Mi"
              cpu: "250m"
            limits:
              memory: "512Mi"
              cpu: "1000m"
      volumes:
        - name: plano-config
          configMap:
            name: plano-config
---
apiVersion: v1
kind: Service
metadata:
  name: plano
spec:
  selector:
    app: plano
  ports:
    - name: llm-gateway
      port: 12000
      targetPort: 12000