Provider_response added in the SDK

We did add the raw provider_response to our Python and Node SDK. This will give you the flexibility of retrieving model-specific output that we don't provide through our unified API.

See an example response below:

{
  "id": "01J3MZHS6KFEWE7WBSAG0JP25X",
  "created": "2024-07-25T12:58:41.235Z",
  "object": "image",
  "model": "leonard-vision-xl",
  "provider": "leonardoai",
  "is_final": true,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "url": "https://cdn.leonardo.ai/users/3bf1a64b-57f6-499b-907d-8b1286c1aa95/generations/dee000c8-7b6d-4d8c-82b4-d1992f8adce2/Default_a_tree_0.jpg"
      },
      "finish_reason": "stop"
    }
  ],
  "provider_response": {
    "generations_by_pk": {
      "generated_images": [
        {
          "url": "https://cdn.leonardo.ai/users/3bf1a64b-57f6-499b-907d-8b1286c1aa95/generations/dee000c8-7b6d-4d8c-82b4-d1992f8adce2/Default_a_tree_0.jpg",
          "nsfw": false,
          "id": "f47939ed-0841-48fa-b763-50e2e5b02e9a",
          "likeCount": 0,
          "motionMP4URL": null,
          "generated_image_variation_generics": []
        }
      ],
      "modelId": "5c232a9e-9061-4777-980a-ddc8e65647c6",
      "motion": null,
      "motionModel": null,
      "motionStrength": null,
      "prompt": "a tree",
      "negativePrompt": "",
      "imageHeight": 512,
      "imageToVideo": null,
      "imageWidth": 512,
      "inferenceSteps": 15,
      "seed": 4135326353,
      "public": false,
      "scheduler": "EULER_DISCRETE",
      "sdVersion": "SDXL_0_9",
      "status": "COMPLETE",
      "presetStyle": "CINEMATIC",
      "initStrength": null,
      "guidanceScale": null,
      "id": "dee000c8-7b6d-4d8c-82b4-d1992f8adce2",
      "createdAt": "2024-07-25T12:58:43.034",
      "promptMagic": false,
      "promptMagicVersion": null,
      "promptMagicStrength": null,
      "photoReal": false,
      "photoRealStrength": null,
      "fantasyAvatar": null,
      "generation_elements": []
    }
  }
}