AI Infrastructure Platform

Hanzo Cloud
AI at Scale

Our enso and Zen models, served first-party. Usage analytics, team management, and API key provisioning — all in one platform.

api.hanzo.ai
curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-hanzo-..." \
  -d '{
    "model": "zen5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
enso + Zen
First-Party Models
<50ms
Added Latency
Multi-region
Automated failover
5000
Req/s Capacity

Everything you need for AI infrastructure

From a single API key to a full enterprise deployment. Hanzo Cloud scales with your team.

AI API

Chat, embeddings, images and reranking on one host. Our own enso and Zen models served first-party, with outside models on the same key.

Usage Analytics

Real-time token usage, cost tracking, and performance metrics. Per-model, per-team breakdowns with Datastore-powered dashboards.

Team Management

Organizations, teams, and role-based access control. SSO via Hanzo IAM with granular permissions per API key.

API Key Management

Create, rotate, and scope API keys. Set rate limits, model access, and budget caps per key.

Security & Compliance

End-to-end encryption, audit logs, and SOC 2 Type II controls. PII redaction and content filtering built in.

Rate Limiting & Caching

Intelligent response caching with KV. Global and per-key rate limits. Automatic retry with exponential backoff.

Built for production

Enterprise-grade infrastructure running on Kubernetes with automatic scaling, failover, and observability.

Request Flow
api.hanzo.ai
Cloudflare Edge + TLS
API Gateway
Auth, rate limiting, caching
LLM Router
Provider selection, load balancing, fallback
AI Provider
OpenAI, Anthropic, Together, Deepseek...
Analytics Pipeline
Langfuse → Datastore → Dashboards

Ready to get started?

Sign in to the Hanzo App to manage your AI infrastructure. Create API keys, monitor usage, and manage your team.