# Models

URL: https://docs.hanzo.ai/docs/chat/models

> Which models Hanzo Chat can reach, and how to choose and configure them in chat.yaml.

Hanzo Chat talks to the Hanzo AI API, so it can reach **every model the gateway
serves** — the enso and Zen families, and the models we carry from outside labs,
on one key.

Which models those are, and what each costs, is one list and it lives at
[**Models**](https://docs.hanzo.ai/docs/openapi/ai). It is fetched from the gateway as you read it, so it
is right today; the hand-written table that used to sit here named a `zen4`
family the gateway has since retired, at prices that were never updated. That is
what a second copy of a catalogue always becomes.

This page covers the part that is Chat's own: choosing and configuring which of
those models Chat offers you.

## Recommendations

Pick by the shape of the job, then copy the id from the catalogue:

| Use case             | Reach for                                                                                                                          |
| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| General chat         | `enso-auto` — free models, or on a paid plan the [Enso tier](https://docs.hanzo.ai/docs/models/enso) your reasoning depth asks for |
| Volume, fast answers | `enso-flash`                                                                                                                       |
| Coding and analysis  | `enso-pro`                                                                                                                         |
| The hardest problems | `enso-ultra`                                                                                                                       |
| Code generation      | `zen5-coder`                                                                                                                       |
| Vision               | `zen-vl`                                                                                                                           |
| Content moderation   | `zen-guard`                                                                                                                        |
| Embeddings           | `zen-embedding`                                                                                                                    |

## Configuring Models

### Via chat.yaml

```yaml
endpoints:
  hanzo:
    baseURL: "https://api.hanzo.ai/v1"
    apiKey: "${HANZO_API_KEY}"
    models:
      default:
        - zen5
        - zen5-coder
        - zen5-mini
      fetch: true  # Auto-discover additional models

  openAI:
    apiKey: "${OPENAI_API_KEY}"
    models:
      default:
        - gpt-4o
        - o3
```

### Auto-Discovery

Set `fetch: true` on any endpoint to automatically discover available models from the API. This is useful when new models are added — they appear without config changes.

### Custom Display Names

```yaml
endpoints:
  hanzo:
    modelDisplayLabel: "Zen"
    iconURL: "https://cdn.hanzo.ai/img/logo-white.svg"
```

## Pricing

- **$5 free credit** on every new account (expires in 30 days)
- **Prepaid billing** — add credits at [platform.hanzo.ai](https://platform.hanzo.ai)
- **$1 minimum balance** required for API calls
- **No surprise bills** — service stops when credits are depleted

Per-model rates are on the [Pricing](https://docs.hanzo.ai/docs/pricing) page.