## List supported models

**get** `/api/v1/models`

Lists the models currently available to the caller through the responses endpoint: hosted models, harnesses and inference stacks. Pass `type=hosted` for the hosted models alone: what the caller's key grants, minus the `-direct` ids, which are omitted rather than listed under the public name they serve. The catalogue only supplies the `display_name` when it carries the model. An approved inference provider key receives the provider catalog representation instead.

### Query Parameters

- `type: optional "hosted"`

  Narrows the list to the hosted models the caller's key grants, leaving out harnesses and stacks. A `-direct` id is omitted rather than listed under the public name it serves, and a granted model the catalogue does not carry is still listed, without a `display_name`.

  - `"hosted"`

### Header Parameters

- `"X-Organization-Id": optional string`

### Returns

- `object: "list"`

  - `"list"`

- `data: array of object { id, created, object, 3 more }`

  - `id: string`

    Model identifier accepted by the responses endpoint.

  - `created: number`

    Unix timestamp when the model was created.

  - `object: "model"`

    - `"model"`

  - `owned_by: string`

    Organization that owns the model.

  - `display_name: optional string`

    Human-readable name, when the model is one the platform catalogues.

  - `shutdown_date: optional string`

    Date when the model will be shut down, if announced.

### Example

```http
curl https://api.prod.adaptionlabs.ai/api/v1/models \
    -H "Authorization: Bearer $ADAPTION_API_KEY"
```

#### Response

```json
{
  "object": "list",
  "data": [
    {
      "id": "qwen3.5-397b",
      "created": 1750000000,
      "object": "model",
      "owned_by": "platform",
      "display_name": "Qwen 3.5 397B",
      "shutdown_date": null
    }
  ]
}
```