Extract asynchronously

Submit one document and retrieve the result later.

POST /extract

Use this endpoint when extraction can continue after the request ends. The response returns an extraction identifier. Retrieve its result later or receive a webhook.

Request

Send content or file_url. Use documentType for one extraction. Use documentTypes for multi-extraction.

Common options include model, extractionFormat, extractionPrompt, metadata, and includeLayout.

Shared request parameters

Property	Type	Description
additionalParams	AdditionalParams	Fine-grained extraction options.
agentInstructions	string	System-level LLM instructions.
analysisDepth	string	quick or standard analysis.
chartOfAccounts	object or array	Chart-of-accounts mapping.
chartOfAccountsUrl	string	URL for chart-of-accounts JSON.
content	string	Base64-encoded file content.
custom_document_types	array	Custom V2 classification types.
documentType	string	One document type. Excludes documentTypes.
documentTypes	array<DocumentTypeEntry>	Multiple document types. Excludes documentType.
enableCaching	boolean	Cache the extraction result.
enableDocumentAnalysis	boolean	Run V2 document analysis.
enableJudge	boolean	Run post-extraction LLM evaluation.
enablePageContent	boolean	Return OCR content and summaries by page.
enablePageSummaries	boolean	Deprecated. Use enablePageContent.
enableRawSections	boolean	Return OCR sections and bounding boxes.
extractionFormat	object	Custom output JSON schema.
extractionPrompt	string	Custom extraction instruction.
file_url	string	Reachable document URL.
form8825Address	string	One Form 8825 property address.
form8825Addresses	array	Form 8825 property addresses.
formTypes	array	Tax document form types.
galleryIds	array	Knowledge Search galleries to tag.
includeLayout	boolean	Return document layout structure.
industry	string	Industry for the default chart of accounts.
metadata	object	Extraction record metadata.
model	string	gpt-4.1, gpt-5.1, gemini-3, or supported OpenRouter model.
overrideCache	boolean	Bypass a cached result.
query	string	Question to answer after extraction.
quickExtract	boolean	Use Gemini native PDF extraction.
rawExtractionOnly	boolean	Return OCR and layout only.
subtype	string	Document subtype.
tagInstructions	string	Tag instructions for OtherWithMetadata.

Nested objects

AdditionalParams

Property	Type	Description
extractImages	boolean	Extract images from well-formatted PDFs.
imageInstructions	string	Vision-tag and rank extracted images.
returnFieldConfidences	boolean	Return confidence scores for extracted fields.

DocumentTypeEntry

Property	Type	Description
documentType	string	Document type for extraction.
entity	string	Entity name.
entityId	string	Entity identifier.
pageNumbers	array	PDF pages to extract.
sheetNames	array	Excel sheets to extract.

Responses

Status	Description	Schema
200	Extraction accepted for one document type.	ExtractResponse
202	Extraction accepted for multiple document types.	ExtractResponse
400	Invalid request.	ValidationError
401	API key is missing or invalid.
500	Missing or invalid request body. Known defect.

curl -X POST "https://<api-host>/extract" \
  -H "X-Api-Key: $DOCAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
        "documentType": "BankStatements",
        "file_url": "https://example.com/statement.pdf"
      }'

Use Retrieve extraction results to fetch the completed extraction.