Skip to main content
POST
Extract

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
schema
any
required

The JSON schema to use for extraction.

document_url
required

The URL of the document to be processed. You can provide one of the following:

  1. A publicly available URL
  2. A presigned S3 URL
  3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document
  4. A job_id (jobid://) or a list of job_ids (jobid://) obtained from a previous /parse endpoint
options
BaseProcessingOptions · object
advanced_options
AdvancedProcessingOptions · object
experimental_options
ExperimentalProcessingOptions · object
system_prompt
string
default:Be precise and thorough.

A system prompt to use for the extraction. This is a general prompt that is applied to the entire document before any other prompts.

deep_extract
boolean
default:false

If True, use Deep Extract, an agentic extraction mode that iteratively refines its output to achieve near-perfect accuracy. Best for complex documents where accuracy is critical.

force_url_result
boolean
default:false

Force the endpoint result to be returned in URL form.

generate_citations
boolean
default:false

If citations should be generated for the extracted content.

array_extract
ArrayExtractConfig · object

The configuration options for array extract

use_chunking
boolean
default:false

If chunking should be used for the extraction. Defaults to False.

include_images
boolean
default:false

If images should be passed directly for extractions. Can only be enabled for documents with less than 10 pages. Defaults to False.

spreadsheet_agent
boolean
default:false

If spreadsheet agent should be used for extraction.

experimental_table_citations
boolean
default:true

If table citations should be generated for the extracted content.

priority
boolean
default:true

If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs.

citations_options
AdvancedCitationsConfig · object

The configuration options for citations.

agent_extract
AgentExtractConfig · object

The configuration options for agent extract

Response

Successful Response

The response is of type Response Extract Extract Post · object.