Search
K
Models API

Upload a file

Upload a file (image or video) to be used as input for predictions.
The uploaded file will be stored temporarily and can be referenced in prediction
requests by its URL.

Uploaded files are available for 30 minutes after upload
and are automatically deleted after expiration. Use the returned URL in
your prediction input fields that accept file URLs.

Rate limit: 10000 requests per minute

Example with curl:

curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: YOUR_API_KEY" \
  -F "content=@/path/to/your/file.jpg"

Note: Use -F (form) with @ prefix to upload a file from your local filesystem.

post
https://api.pruna.ai/v1/files

Body

multipart/form-data
contentstringrequired

The file to upload (image or video)

Response

application/json

File uploaded successfully

FileUploadResponse

idstringrequired

Unique identifier for the uploaded file

Example:fqadqq42xq

namestringrequired

Original filename

Example:test.jpg

content_typestringrequired

MIME type of the uploaded file

Example:image/jpeg

sizeintegerrequired

File size in bytes

Example:185093

etagstring

Entity tag for cache validation

Example:"14e9a51deaac6bee2dd8b5c52d7d0b5f"

checksumsobject

File integrity checksums

Show Child Parameters
metadataobject

Additional file metadata (varies by file type)

Show Child Parameters
created_atstring(date-time)required

Timestamp when the file was uploaded

Example:2025-01-08T18:51:26.729Z

expires_atstring(date-time)required

Timestamp when the file will expire and be deleted

Example:2025-01-09T18:51:26.729Z

urlsobjectrequired

URLs to access the uploaded file

Show Child Parameters
post/v1/files

Body

{ "content": "content" }
 
application/json

Content Delivery

Download generated content files

Download generated content

Download the generated content file. This is the third and final
step in the workflow.

Use the generation_url from the prediction status response directly - no path extraction needed.
Simply make a GET request to that URL with your API key.

Rate limit: 10,000 requests per minute.

get
https://api.pruna.ai/v1/predictions/delivery/{path}

Path Parameters

pathstringrequired

The delivery path returned in the prediction status response

Example:xezq/52UGYRrRfqViaKmvYsEnENTh0qLDAWHptQ8jOnEHu7XC6AtKA/output_42_0.jpeg

Response

Content file downloaded successfully

string

Generated image file

get/v1/predictions/delivery/{path}
 

PredictionRequest

object
inputobjectrequired

Model-specific input parameters

* Additional properties are allowed.
Example

PredictionResponse

object
idstringrequired

Unique identifier for the prediction

Example:1zww7deyssrme0csqwr90phzzr

modelstringrequired

Model identifier used for this prediction

Example:vace

inputobjectrequired

The input parameters provided for this prediction

* Additional properties are allowed.
get_urlstring(uri)required

URL to check prediction status

Example:https://api.pruna.ai/v1/predictions/status/1zww7deyssrme0csqwr90phzzr

Example