Hanzo/ blog
Back to all articles
edgegatewayapiinfrastructurelaunch

Hanzo Edge: High-Performance API Gateway

Introducing Hanzo Edge — a high-performance API gateway with sub-millisecond routing, rate limiting, and authentication at the edge.

API gateways sit on the critical path of every request. Latency added by the gateway is latency added to every API call. Most gateways add 5-50ms of overhead. For high-frequency APIs, that is unacceptable.

Today we are launching Hanzo Edge: an API gateway with sub-millisecond routing overhead.

Performance

  • Routing latency: < 1ms p99
  • Throughput: 100K+ requests per second per instance
  • TLS termination: Hardware-accelerated, adds < 0.5ms

The gateway is written in Rust for predictable performance without garbage collection pauses.

Features

Request Routing

  • Path-based and header-based routing
  • Weighted traffic splitting for canary deployments
  • URL rewriting and path manipulation
  • WebSocket support

Rate Limiting

  • Per-consumer, per-route, and global rate limits
  • Sliding window algorithm for smooth limiting
  • Rate limit headers in responses
  • Custom response codes and messages

Authentication

  • API key validation at the edge
  • JWT verification without hitting your backend
  • OAuth 2.0 token introspection
  • mTLS for service-to-service communication

Transformation

  • Request/response header manipulation
  • Body transformation (JSON to XML and back)
  • GraphQL to REST translation
  • Response caching with configurable TTL

Observability

  • Request logging with configurable verbosity
  • Latency histograms per route
  • Error rate tracking
  • Integration with Hanzo Observability

Configuration

Declarative configuration:

routes:
  - path: /api/v1/users
    upstream: user-service:8080
    rate_limit:
      requests: 1000
      window: 60s
    auth:
      type: jwt
      issuer: https://hanzo.id

  - path: /api/v1/public
    upstream: public-service:8080
    cache:
      ttl: 300s

Pricing

  • Free: 1M requests/month
  • Pro: $49/month — 100M requests, all features
  • Enterprise: Unlimited requests, dedicated instances

Hanzo AI is Techstars '17.

Read more

One API for Every AI Model: Introducing the Hanzo AI Gateway

Hanzo AI launches the industry's first zero-markup multi-provider AI gateway — one API key for 100+ models from every major provider, plus 14 proprietary Zen models.

The Hanzo API Gateway

Introducing the Hanzo API Gateway: unified access, better security, and improved developer experience.

Introducing Enso — one API, routed to the best frontier intelligence

Enso is Hanzo's learned router: no single frontier model leads every benchmark, so Enso routes each request to the model most likely to win it — and learns from your feedback as it goes. Microsecond routing on a CPU, a transparent per-request meter, and a 1% fee that pays for itself. Here is how it works, the measured results, and the cost-transparency angle a monolith cannot offer.