Use Hanzo AI with Kubernetes
Deploy Hanzo AI-powered workloads on Kubernetes. Securely manage your Hanzo API key as a K8s secret and inject it into pods.
Get API key — FreeapiVersion: v1
kind: Secret
metadata:
name: hanzo-credentials
namespace: default
type: Opaque
stringData:
api-key: "your-hanzo-api-key"
2 of 8 lines point at Hanzo
Base URL: https://api.hanzo.ai/v1
API Key: Get yours at platform.hanzo.ai/api-keys · Fully OpenAI-compatible · 400+ models available
Deployment manifest
yaml
3 of 22 lines point at Hanzo
apiVersion: apps/v1
kind: Deployment
metadata:
name: ai-service
spec:
replicas: 2
selector:
matchLabels:
app: ai-service
template:
spec:
containers:
- name: app
image: my-ai-app:latest
env:
- name: HANZO_API_KEY
valueFrom:
secretKeyRef:
name: hanzo-credentials
key: api-key
- name: OPENAI_API_BASE
value: "https://api.hanzo.ai/v1"
Apply to cluster
bash
2 of 4 lines point at Hanzo
kubectl create secret generic hanzo-credentials \
--from-literal=api-key="your-hanzo-api-key"
kubectl apply -f deployment.yaml
kubectl get pods -l app=ai-service
HPA for AI workloads
yaml
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: ai-service-hpa
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: ai-service
minReplicas: 2
maxReplicas: 10
metrics:
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: 70
Created by CNCF / Google
License: Apache-2.0 · View source on GitHub →
Hanzo AI is OpenAI-compatible, so existing Kubernetes code works with zero refactoring. We deeply appreciate the CNCF / Google team for building and maintaining this open-source project.
Ready to get started?
Create a free account and get your API key. The Free plan includes free model requests and Kai decisions, no card.