Extract Data

Extract structured data from PDF documents using custom schemas with vision-language models. Supports multiple model tiers, optional bounding box citations, and intelligent page selection for large documents.

post/v2/extract

Request

  • Base URL: https://prod.visionapi.unsiloed.ai
  • URL: https://prod.visionapi.unsiloed.ai/v2/extract
  • Auth: API key in header api-key

Response

Successful response

job_idstring

Unique identifier for the extraction job

statusstring

Initial job status (typically 'queued')

messagestring

Descriptive message about the job creation

quota_remainingnumber

Number of Credits remaining in your quota

Changes

No recorded changes to this operation across all 1 revision of this API.