Hanzo

Models

The live Hanzo model catalog and pricing — every model served through api.hanzo.ai/v1, with context windows and per-token cost.

Models

API reference · Models → — every endpoint, generated from the OpenAPI spec.

The catalogue lives at Models — every model the gateway serves, fetched live as you read, with the id you pass as model and its current rate. It used to be rendered here too; one catalogue, one URL.

This page is the service note: how the model surface behaves once you have picked an id.

Using a model

Pass the model id straight into the request:

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen5",
    "messages": [{ "role": "user", "content": "What is the meaning of life?" }]
  }'

Swapping models is a one-string change — zen5 (default), zen5-coder for code, zen5-flash for speed, or enso for the frontier reasoning tier:

import Hanzo from '@hanzo/ai';

const client = new Hanzo({ apiKey: process.env.HANZO_API_KEY });

const res = await client.chat.completions.create({
  model: 'enso',
  messages: [{ role: 'user', content: 'Explain quantum entanglement.' }],
});

Listing models programmatically

The same catalog is available over HTTP — each entry carries its context, pricing (USD per 1M tokens), features, and family:

curl https://api.hanzo.ai/v1/models
{
  "object": "list",
  "data": [
    {
      "id": "zen5",
      "name": "Zen5 (Default)",
      "context": 1000000,
      "pricing": { "input": 4.176, "output": 13.2, "cacheRead": 0, "cacheWrite": null },
      "features": ["chat", "tools", "vision"],
      "provider": "Hanzo"
    }
  ],
  "families": [ { "id": "enso", "name": "Enso", "models": ["enso", "enso-flash", "enso-ultra"] } ],
  "summary": { "totalModels": 35 }
}

What the frontier tier is and when to reach for it — Flash, Pro, Ultra

The open-weight family, from 4B edge to 1T+ reasoning

The API gateway in front of every model

The GPU inference engine serving the Zen and Enso families

Programmatic pricing for models, cloud, GPUs, and plans

Try the models in the hosted chat UI

How is this guide?

On this page