Internet
                       |
          +-----------+-----------+
          |                       |
   Cloudflare              DO Load Balancer
   api.hanzo.ai            api.lux.network
          |                       |
          v                       v
 +------------------+   +------------------+
 | hanzo-k8s        |   | lux-k8s          |
 | Gateway (2 pods) |   | Gateway (2 pods) |
 | port 8080        |   | port 8080        |
 +--------+---------+   +--------+---------+
          |                       |
    +-----+-----+          +-----+-----+
    |           |          |           |
 /v1/*      /commerce/*  /ext/bc/C/rpc  /ext/bc/X
    |           |          |              |
    v           v          v              v
 cloud-api  commerce    luxd:9630      luxd:9630
  :8000      :8001     (mainnet)      (mainnet)

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic-claude-haiku-4.5",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in one paragraph."}
    ],
    "max_tokens": 256
  }'

{
  "id": "chatcmpl-abc123",
  "object": "chat.completions",
  "created": 1740000000,
  "model": "anthropic-claude-haiku-4.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing leverages quantum mechanical phenomena..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 85,
    "total_tokens": 97
  }
}

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai-gpt-5-nano",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

curl https://api.hanzo.ai/v1/embeddings \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

curl https://api.hanzo.ai/v1/images/generations \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A futuristic city skyline at sunset",
    "n": 1,
    "size": "1024x1024"
  }'

curl https://api.hanzo.ai/v1/models \
  -H "Authorization: Bearer $HANZO_API_KEY"

from hanzoai import Hanzo

client = Hanzo(api_key="your-key")

response = client.chat.completions.create(
    model="zen4-pro",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import Hanzo from '@hanzo/ai'

const client = new Hanzo({ apiKey: 'your-key' })

const response = await client.chat.completions.create({
  model: 'zen4-pro',
  messages: [{ role: 'user', content: 'Hello!' }]
})
console.log(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    api_key="your-hanzo-key",
    base_url="https://api.hanzo.ai/v1"
)

response = client.chat.completions.create(
    model="openai-gpt-5-nano",
    messages=[{"role": "user", "content": "Hello!"}]
)

zen4-pro
zen4-mini
openai-gpt-5-nano
anthropic-claude-haiku-4.5
meta-llama-3.3-70b-instruct
mistral-small-3.1-24b-instruct
google-gemini-2.0-flash-001

github.com/hanzoai/gateway/v2  (Go 1.25)

Deployment (2 replicas)
  image: ghcr.io/hanzoai/gateway:<cluster>-latest
  port: 8080
  resources:
    requests: 100m CPU, 128Mi RAM
    limits: 1 CPU, 512Mi RAM
  probes:
    liveness:  GET /__health (every 15s)
    readiness: GET /__health (every 5s)
  config: ConfigMap → /etc/gateway/gateway.json

# Validate configs
make validate

# Deploy to hanzo-k8s
make deploy-hanzo

# Deploy to lux-k8s
make deploy-lux

# Deploy both
make deploy

# Check status
make status

# Tail logs
make logs-hanzo
make logs-lux

configs/
  hanzo/gateway.json    # Hanzo API Gateway (15+ services)
  lux/gateway.json      # Lux blockchain RPC (14 endpoints)
k8s/
  hanzo/                # deployment, service, ingress
  lux/                  # deployment, service
Dockerfile              # Multi-stage build (Go build + Alpine runtime)
Makefile                # Build, validate, deploy commands

# Gateway internal health
curl https://api.hanzo.ai/__health

# Public health endpoint
curl https://api.hanzo.ai/health

# Lux gateway health
curl https://api.lux.network/ext/health

Internet -> Ingress (TLS/L7) -> Gateway (API routing) -> Engine (inference) / Cloud API / Services
                                                          Edge (on-device, client-side)