/v1/schemas/worldlabs/world/marble/v1/operations/{operation_id}?kind=output
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace4a3ed614672e0b640de378db458907865a4e9c05499482f1e2a79fba5977eebe{
"fetchedAt": 1794287457,
"extractorVersion": "2",
"verifiedAt": null
} |
Response body
9 properties · 2 required · 20 $defs| property | type | description | constraints |
|---|---|---|---|
| done* | boolean | True if the operation is completed | |
| operation_id* | string | Operation identifier | |
| cost | OperationCost | Settled credit cost for a successful operation. | nullable |
| created_at | string | Creation timestamp | format: date-time · nullable |
| error | OperationError | Error information for a failed operation. | nullable |
| expires_at | string | Expiration timestamp | format: date-time · nullable |
| metadata | object | Service-specific metadata, such as progress percentage | nullable |
| response | World | PanoDepthToRgbResult | ExportWorldResult | Result payload when done=true and no error. Structure depends on operation type. | nullable |
| updated_at | string | Last update timestamp | format: date-time · nullable |
Types
20 $defsContentobject
Represents content (media, text, images) that can be stored inline or via URL.
| data_base64 | string | nullable | |
| extension | string | File extension without dot | nullable |
| uri | string | nullable |
DepthPanoPromptobject
For models conditioned on a depth pano and text. When depth_pano_image is a log-encoded PNG, z_min and z_max are required to decode it correctly. When it is an EXR file containing raw float depth values, z_min and z_max will both be ignored. Please set z_min a…
| depth_pano_image* | Content | Represents content (media, text, images) that can be stored inline or via URL. | |
| text_prompt | string | nullable | |
| type | const | "depth-pano" · default: "depth-pano" | |
| z_max | number | nullable | |
| z_min | number | nullable |
ExportWorldResultobject
Downloadable exported world asset.
| asset_type* | enum | Exported asset family | splats | mesh |
| format* | enum | Exported file format | ply | glb |
| mesh_variant | enum | Mesh variant returned for this export, if applicable | textured | vertex_colored · nullable |
| resolution | string | Splat resolution used for this export, if applicable | nullable |
| url* | string | Download URL for the exported asset |
ImageryAssetsobject
Imagery asset URLs.
| pano_url | string | Panorama image URL | nullable |
InpaintPanoPromptobject
For models that inpaint the masked portion of a pano image.
MeshAssetsobject
Mesh asset URLs.
| collider_mesh_url | string | Collider mesh URL | nullable |
| full_res_mesh_url | string | Full-resolution vertex-colored mesh URL | nullable |
| hq_mesh_url | string | High-quality textured mesh URL | nullable |
MultiImagePrompt-Outputobject
For world models supporting multi-image (+ text) input.
| multi_image_prompt* | SphericallyLocatedContent-Output[] | ||
| reconstruct_images | boolean | default: false | |
| text_prompt | string | nullable | |
| type | const | "multi-image" · default: "multi-image" |
OperationCostobject
Settled credit cost for a successful operation.
| line_items | OperationCostLineItem[] | Usage events that make up the operation's total credits | |
| total_credits* | integer | Total credits charged for the operation |
OperationCostLineItemobject
A single usage event contributing to an operation's total credits.
| credits* | integer | Credits charged for this usage event | |
| name* | string | Human-readable usage event name |
OperationErrorobject
Error information for a failed operation.
| code | integer | Error code | nullable |
| message | string | Error message | nullable |
PanoDepthToRgbResultobject
Result from depth-to-RGB panorama generation.
| pano_url | string | URL of the generated RGB panorama image. Available when the operation succeeds. | nullable |
Permissionobject
Access control permissions for a resource.
| allow_id_access | boolean | default: false | |
| allowed_readers | string[] | ||
| allowed_writers | string[] | ||
| public | boolean | default: false |
Promptobject
For world models generating a world from a single image (+ text). Images can be generated using the :image-generation method. If no text prompt is provided, it will be generated via recaption.
| image_prompt* | Content | Represents content (media, text, images) that can be stored inline or via URL. | |
| is_pano | boolean | default: false | |
| text_prompt | string | nullable | |
| type | const | "image" · default: "image" |
SphericallyLocatedContent-Outputobject
Content with a preferred location on the sphere.
| azimuth | number | nullable | |
| data_base64 | string | nullable | |
| extension | string | File extension without dot | nullable |
| uri | string | nullable |
SplatAssetsobject
Gaussian splat asset URLs.
| semantics_metadata | WorldSemanticsMetadata | Semantic metadata describing how to interpret the generated splat asset in real-world units. | nullable |
| spz_urls | object | URLs for SPZ format Gaussian splat files | nullable |
VideoPrompt-Outputobject
For world models supporting video (+ text) input.
| text_prompt | string | nullable | |
| type | const | "video" · default: "video" | |
| video_prompt* | Content | Represents content (media, text, images) that can be stored inline or via URL. |
Worldobject
A generated world, including asset URLs.
| assets | WorldAssets | Downloadable outputs of world generation. | nullable |
| created_at | string | Creation timestamp | format: date-time · nullable |
| display_name* | string | Display name | |
| model | string | Model used for generation | nullable |
| permission | Permission | Access control permissions for a resource. | nullable |
| tags | string[] | Tags associated with the world | nullable |
| updated_at | string | Last update timestamp | format: date-time · nullable |
| world_id* | string | World identifier | |
| world_marble_url* | string | World Marble URL | |
| world_prompt | WorldTextPrompt | Prompt | MultiImagePrompt | … | World prompt | nullable |
WorldAssetsobject
Downloadable outputs of world generation.
| caption | string | AI-generated description of the world | nullable |
| imagery | ImageryAssets | Imagery asset URLs. | nullable |
| mesh | MeshAssets | Mesh asset URLs. | nullable |
| splats | SplatAssets | Gaussian splat asset URLs. | nullable |
| thumbnail_url | string | Thumbnail URL for the world | nullable |
WorldSemanticsMetadataobject
Semantic metadata describing how to interpret the generated splat asset in real-world units.
| ground_plane_offset | number | Vertical (Y-axis) offset, in meters, of the detected ground plane in the metric-scaled frame. Subtract from Y after applying `metric_scale_factor` to place the ground at y=0. | nullable |
| metric_scale_factor | number | Multiplicative factor that converts raw asset coordinates to meters. Multiply all XYZ positions (and isotropic scales) by this value. A value of 1.0 means scale could not be inferred and the asset was left in model units. | nullable |
WorldTextPrompt-Outputobject
Input prompt class for text-conditioned world generation.
| text_prompt | string | nullable | |
| type | const | "text" · default: "text" |
Validate a payload
before you spend tokens$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"worldlabs","endpointId":"marble/v1/operations/{operation_id}","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}