Serverless AI Image Content Extraction

AI powered OCR service that extracts specific text content from images based on the provided content keys.

Endpoint

This API uses multipart/form-data format. You must send the image file and the contents as form fields.

POSThttps://api.xtartapp.com/image/content-extraction

You must use a Bearer token provided by the dashboard to use for authentication. Add the token to the Authorization header.

Name	Type	Required	Max	Description
image	File	Yes	-	The image file to analyze. Must be provided as a file in multipart/form-data.
contents	string	Yes	20 items	A JSON string containing an array of content keys and descriptions to extract from the image. Maximum 20 items. Format: '[{"key":"example_key","description":"description text"}]'
contents[].key	string	Yes	25	The key for the content to extract from the image.
contents[].description	string	Yes	150	A description of the content to extract.

Name	Type	Description
data	object	An object containing all extracted content with keys matching the input content keys
data.<key>	string	The extracted key for the specified content key
data.<value>	string	The extracted value about the extracted key
metadata	object	Metadata about the image analysis process
metadata.cost	number	The cost of the image extraction request

{
   "error": "string", 
   "code": "string"
}

HTTP Status	Error Code	Message
400	INVALID_PAYLOAD	Occurs when the payload is invalid.
400	INVALID_REQUEST	The request is invalid.
400	IMAGE_CONTENT_EXTRACTION_ERROR	Could not extract content from image \| parsing error.
400	INVALID_IMAGE	The image was not found or is invalid.
400	HARM_CONTENT	The content is harmful and cannot be processed.
400	INSUFFICIENT_BALANCE	The user has insufficient balance.
401	UNAUTHORIZED	The token is invalid.
429	TOO_MANY_REQUESTS	The request limit has been reached.