Skip to main content
POST

Body

string
The image url.
string
The key used to store the image on Jigsawstack file. Learn more about how to handle files in Jigsawstack’s Handling Files section.
string | Array<string> | object
The prompt used to describe the image. Default prompt is Describe the image in detail.
boolean
Enables enhanced OCR processing to improve bounding box accuracy for detected text elements.
Array<number>
Specifies a range of pages to process with vOCR, provided as a two-element array: [startPage, endPage]. For example, [1,10] processes pages 1 through 10. The range must span 10 or fewer pages. If the specified endPage exceeds the document’s total pages, the last available page will be used instead. Both startPage and endPage are inclusive and must be positive integers where startPage ≤ endPage.
Either url or file_store_key should be provided not both.

Prompt Example

  • String
  • Array<String>
Use this approach to retrieve specific data from the image file.
string
required
Your JigsawStack API key

Response

boolean
Indicates whether the call was successful.
object
Usage information for the API call.
string
A unique identifier for the request
string | object
When using a string prompt: Returns the descriptive text about the image. When using an array prompt: Returns an object with keys matching the prompt items and values as arrays of extracted data.
number
The width of the processed image in pixels.
number
The height of the processed image in pixels.
string[]
Array of automatically generated tags describing the content of the image.
boolean
Indicates whether text was detected in the image.
array
Array of text sections detected in the image with detailed positioning information.
number
The total number of pages in the document. Only available for PDF files.
number[]
The range of pages that were processed. Only available when page_range parameter is specified in the request.
Supported file types: - Images: JPEG, JPG, PNG - Documents: Multi-page PDFs (up to 10 pages per API request)