# ML

URL: https://docs.hanzo.ai/docs/cli/ml

> The `hanzo ml` commands.

Also for this capability: [API](https://docs.hanzo.ai/docs/openapi/ml) · **CLI** · [SDKs](https://docs.hanzo.ai/docs/sdks)

Model serving: deploy a model behind an endpoint and call it.

[API reference →](https://docs.hanzo.ai/docs/openapi/ml)

```bash
hanzo ml models list
```

Every command takes `--json` for the raw response and `--help` for its own flags. Sign in once with `hanzo auth login`; the commands below use that session, and the org they act in is the one it carries.

| Command           | What it does                                      |
| ----------------- | ------------------------------------------------- |
| `hanzo ml health` | Whether model serving can actually work right now |

### Models

| Command                          | What it does                                                                                                |
| -------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| `hanzo ml models create`         | Deploys one inference model for the caller's org, and answers 201 with the model as Kubernetes admitted it. |
| `hanzo ml models get <name>`     | Returns one deployed inference model.                                                                       |
| `hanzo ml models list`           | Lists the inference models deployed in the caller's org.                                                    |
| `hanzo ml models predict <name>` | Run inference against one of your deployed models                                                           |
| `hanzo ml models rm <name>`      | Deletes a deployed inference model.                                                                         |
| `hanzo ml models update <name>`  | Change a deployed model in place                                                                            |