Gateway

The Hanzo Gateway is the single front door to the platform. Every request to api.hanzo.ai lands here: it authenticates the caller, enforces rate limits and quotas, meters usage for billing, and routes to the right backend. One base URL, one key, every service.

Gated and Priced

"Gated" and "priced" are the gateway's job:

• Gated -- the gateway rejects unauthenticated or over-quota requests before they reach a backend. Present an API key (sk-...) or an IAM bearer token. Rate limits and circuit breakers protect every downstream service.
• Priced -- metered usage is attributed to your organization and priced by the commerce subsystem. See Billing for credits, metering, and invoices.

The gateway forwards your Authorization header unchanged and streams responses (SSE) without transformation, so an HTTP client written against the chat-completions shape works against it once its base URL points here.

Traffic Path

Requests flow through three layers before reaching a service:

Internet → Ingress (TLS, L7) → Gateway (auth, rate-limit, routing) → Cloud / service

Ingress terminates TLS and handles L7 routing; the gateway handles authentication, pricing, and per-endpoint routing; the backend service does the work. This is the canonical path for every product.

One Base URL

All services are reached under a single base -- https://api.hanzo.ai/v1 -- namespaced by service (/v1/iam, /v1/kms, /v1/billing, and so on), plus the inference surface at /v1/chat/completions.

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related

• API -- the REST reference for every service behind the gateway
• API Keys -- the credentials the gateway checks
• Billing -- how metered usage is priced
• IAM -- the identity the gateway authenticates
• Hanzo Gateway -- routing tables, clusters, and operations

In this section