> ## Documentation Index
> Fetch the complete documentation index at: https://magica.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Run a model

> Start a standalone model run with API-key authentication.

Use this endpoint to execute one model directly. The response returns a `runId`; poll [`GET /v1/nodes/runs/{runId}`](/api-reference/nodes/get-model-run) for status and output.

For multi-mode models, pass `subModelId` in the JSON body. Discover valid model and sub-model IDs with [`GET /v1/models`](/api-reference/nodes/list-models), [`GET /v1/models/search`](/api-reference/nodes/search), and [`GET /v1/models/{modelId}/schema`](/api-reference/nodes/model-schema).

```bash theme={null}
curl -X POST https://api.magica.com/api/v1/nodes/flux_2_max/run \
  -H "Authorization: Bearer $MAGICA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "subModelId": "flux-2-max-text",
    "input": {
      "prompt": "A cinematic product photo of a glass speaker"
    }
  }'
```