API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Search

Asset Search

search.asset_search(SearchAssetSearchParams**kwargs) -> SyncSearchHitsOffset[SearchAssetSearchResponse]

POST/search/assets

Model Search

search.model_search(SearchModelSearchParams**kwargs) -> SyncSearchHitsOffset[SearchModelSearchResponse]

POST/search/models

ModelsExpand Collapse

class SearchAssetSearchResponse: …

id: str

Unique identifier for the asset (e.g., “asset_GTrL3mq4SXWyMxkOHRxlpw”)

author_id: str

User ID of the asset creator/author

collection_ids: List[str]

Array of collection IDs this asset belongs to

created_at: str

Creation timestamp in ISO 8601 format (e.g., “2025-01-16T11:19:41.579Z”)

metadata: Metadata

Metadata containing detailed information about the asset’s properties and generation parameters

aspect_ratio: Optional[str]

Aspect ratio of the asset (e.g., “1:1”, “16:9”)

base_model_id: Optional[str]

ID of the base model used for generation

guidance: Optional[float]

Guidance scale used for diffusion models to control prompt adherence

height: Optional[float]

Height of the asset in pixels

kind: Optional[str]

Classification of the asset (e.g., “image”, “video”)

model_id: Optional[str]

ID of the specific model used if asset is model-based

model_type: Optional[str]

Type of model used for generation (e.g., “sd-1_5”, “flux.1”)

name: Optional[str]

Custom name given to the asset

negative_prompt: Optional[str]

Negative prompt used during generation to specify what to avoid

negative_prompt_strength: Optional[float]

For Flux models: controls the influence of the negative prompt

num_inference_steps: Optional[float]

Number of inference steps used during generation

parent_job_id: Optional[str]

ID of the parent job that created this asset

prompt: Optional[str]

Text prompt used to generate the asset

scheduler: Optional[str]

Scheduler algorithm used during generation

seed: Optional[str]

Random seed used for generation, enables reproducibility

size: Optional[float]

File size of the asset in bytes

text: Optional[str]

Text used to generate the asset: mainly for speech to text

thumbnail: Optional[MetadataThumbnail]

Thumbnail image information for the asset. Ex. Canvas thumbnail

asset_id: str

ID of the asset used as thumbnail

type: Optional[str]

Specific type/category of the asset (e.g., “canvas”, “inference-txt”)

width: Optional[float]

Width of the asset in pixels

mime_type: str

MIME type of the asset (e.g., “image/png”, “image/jpeg”)

nsfw: List[str]

Array of detected NSFW categories

owner_id: str

Project ID of the asset owner

privacy: str

Privacy setting of the asset (“public”, “private”, or “unlisted”)

tags: List[str]

Array of user-assigned tags for categorization

team_id: str

Team ID of the asset owner

updated_at: str

Last modification timestamp in ISO 8601 format (e.g., “2025-01-16T11:19:41.579Z”)

url: str

Signed URL of the asset

content: Optional[str]

Indexed body for text assets (AssetKind.Text). The full content lives in S3; this field carries up to TEXT_INDEX_MAX_BYTES of UTF-8 for BM25 lookup. Always undefined for non-text assets.

description: Optional[str]

Textual description of the asset. Can be either:

• User-provided description for training images
• Automatically generated caption for images and videos assets
• Automatically generated description for audio assets

score: Optional[float]

Score assigned to the asset based on usage and popularity

thumbnail: Optional[Thumbnail]

Thumbnail preview of the asset 3D, video…

asset_id: str

ID of the asset used as thumbnail

url: str

Signed URL of the thumbnail

transcription: Optional[str]

Transcription of the asset. Can be either:

• Automatically generated transcription for audio assets with speech

class SearchModelSearchResponse: …

id: str

Unique identifier for the model (e.g., “model_GTrL3mq4SXWyMxkOHRxlpw”)

author_id: str

User ID of the model creator/author

capabilities: List[str]

Array of model capabilities

collection_ids: List[str]

Array of collection IDs this model belongs to

concepts: List[Concept]

Array of concept models associated with this model Each concept contains a reference to its source model

model_id: str

ID of the concept’s source model

created_at: str

Creation timestamp in ISO 8601 format (e.g., “2025-01-16T11:19:41.579Z”)

example_asset_ids: List[str]

Array of example asset IDs associated with this model

name: str

Display name of the model

owner_id: str

Project ID of the model owner

privacy: str

Privacy setting of the model (“public”, “private”, or “unlisted”)

short_description: str

Short description of the model

source: str

Source/origin of the model (e.g., “training”, “import”)

tags: List[str]

Array of user-assigned tags for categorization

team_id: str

Team ID of the model owner

training_images_number: float

Number of images used to train this model

type: str

Type of the model (e.g., “sd-1_5”, “flux.1”)

updated_at: str

Last modification timestamp in ISO 8601 format (e.g., “2025-01-16T11:19:41.579Z”)

parent_model_id: Optional[str]

ID of the parent model this model was derived from

score: Optional[float]

Score assigned to the model based on usage and popularity

thumbnail: Optional[Thumbnail]

Thumbnail image information for the model

asset_id: str

ID of the asset used as thumbnail

url: str

Signed URL of the thumbnail