Create models

Deploys one inference model for the caller's org, and answers 201 with the model as Kubernetes admitted it.

POST /v1/ml/models

ML → · All API references → · Get started →


Address	`https://api.hanzo.ai/v1/ml/models`
Method	`POST`
Operation	`post_ml_models`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Deploys one inference model for the caller's org, and answers 201 with the model as Kubernetes admitted it.

The spec is a kserve InferenceService spec, passed through unchanged — this plane owns the tenancy, the billing and the namespace, and kserve owns what a model IS. An unfunded org is refused BEFORE anything is created, so nobody runs free GPU compute and nobody is charged for a resource that was never made.

Request

4 fields, body application/json (required).

Field	In	Type	Required	Description
`labels`	body	object	—	Labels are extra labels to set on the object, merged UNDER the tenancy labels this plane derives from the validated principal — so a label naming another org's…
`labels.*`	body	string	—
`name`	body	string	—	Name is the resource's name: a DNS-1123 label (^a-z0-9?$), lowercased and trimmed.
`spec`	body	any	—	Spec is the resource's own spec, passed to Kubernetes unchanged.

Response

Status	Body	Meaning
`201`	mlResource	created

201 body — 6 fields.

Field	In	Type	Always	Description
`createdAt`	body	string	—	CreatedAt is when Kubernetes admitted the object, RFC 3339 in UTC.
`name`	body	string	—	Name is the object's metadata.name, unique within the caller's namespace.
`spec`	body	object	—	Spec is the resource spec, verbatim as Kubernetes stores it.
`spec.*`	body	object	—
`status`	body	object	—	Status is the live status kserve owns, verbatim.
`status.*`	body	object	—

Failure carries the platform error shape — see Errors.

Examples

hanzo ml models create

import { Configuration, MlApi } from 'hanzoai';

const api = new MlApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postMlModels({ labels: {}, name: "<name>" });

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import MlApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = MlApi(client).post_ml_models(labels={}, name="<name>")

cfg := cloud.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := cloud.NewAPIClient(cfg)

resp, _, err := client.MlAPI.PostMlModels(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_cloud::apis::{configuration::Configuration, ml_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = ml_api::post_ml_models(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.MlApi;

ApiClient client = new ApiClient();
client.setRequestInterceptor(b -> b.header("Authorization", "Bearer " + System.getenv("HANZO_API_KEY")));

var result = new MlApi(client).postMlModels();

curl -X POST https://api.hanzo.ai/v1/ml/models \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "labels": {},
       "name": "<name>"
     }'

MCP reaches ml through the ml tool, which names its 7 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "get_ml_health"
         }
       }
     }'

ML API · All Hanzo APIs · Interactive reference

Request

Response

Examples

On this page