diff --git a/deploy/kubernetes/kub.yaml b/deploy/kubernetes/kub.yaml
new file mode 100644
index 000000000..1ddc0e95f
--- /dev/null
+++ b/deploy/kubernetes/kub.yaml
@@ -0,0 +1,55 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: litellm-deployment
+spec:
+  replicas: 5
+  selector:
+    matchLabels:
+      app: litellm
+  template:
+    metadata:
+      labels:
+        app: litellm
+    spec:
+      containers:
+        - name: litellm-container
+          image: ghcr.io/berriai/litellm:main-latest
+          env:
+            - name: AZURE_API_KEY
+              value: "d699s"
+            - name: AZURE_API_BASE
+              value: "https://openai/"
+            - name: LITELLM_MASTER_KEY
+              value: "sk-1234"
+          ports:
+            - containerPort: 4000
+          args:
+            - "--config"
+            - "/app/proxy_config.yaml"  # Update the path to mount the config file
+          volumeMounts:  # Define volume mount for proxy_config.yaml
+            - name: config-volume
+              mountPath: /app
+              readOnly: true
+          livenessProbe:
+            httpGet:
+              path: /health/liveliness
+              port: 4000
+            initialDelaySeconds: 120
+            periodSeconds: 15
+            successThreshold: 1
+            failureThreshold: 3
+            timeoutSeconds: 10
+          readinessProbe:
+            httpGet:
+              path: /health/readiness
+              port: 4000
+            initialDelaySeconds: 120
+            periodSeconds: 15
+            successThreshold: 1
+            failureThreshold: 3
+            timeoutSeconds: 10
+      volumes:  # Define volume to mount proxy_config.yaml
+        - name: config-volume
+          configMap:
+            name: litellm-config  
diff --git a/deploy/kubernetes/service.yaml b/deploy/kubernetes/service.yaml
new file mode 100644
index 000000000..4751c8372
--- /dev/null
+++ b/deploy/kubernetes/service.yaml
@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: litellm-service
+spec:
+  selector:
+    app: litellm
+  ports:
+    - protocol: TCP
+      port: 4000
+      targetPort: 4000
+  type: LoadBalancer
\ No newline at end of file