Sarvam Parse

Given a PDF, this API helps to get structured extraction of data in the document.The API returns a base64 encoded XML string containing the extracted data.

Headers

api-subscription-keystringRequired

Request

This endpoint expects a multipart form containing a file.
pdffileRequired

Upload the PDF file you want to parse. This should be uploaded as a form input if you’re using multipart/form-data Note: Sarvam Parse supports only English PDFs currently.

page_numberstringOptionalDefaults to 1

The page number you want to extract data from. This is a one-based index (meaning, the first page is 1).

sarvam_modeenumOptional

The mode of parsing to use:

  • small: Use this mode for economical and fast parsing
  • large: Use this mode for highest precision parsing
Allowed values:
prompt_cachingenumOptional

Whether to cache the prompt for the parse request. This is useful when running multiple requests to the parsing endpoint.

Allowed values:

Response

Successful Response

outputstringOptional

The base64 encoded HTML string corresponding to the parsed page. The output will be an empty string if parsing fails for some reason.

Errors