Skip to main content
POST
Extract Structured Data

Authorizations

X-API-Key
string
header
required

Cookies

wos-session
string
datalab_active_team
string

Body

multipart/form-data
file_url
string | null

Optional file URL. Provide either file/file_url or checkpoint_id.

checkpoint_id
string | null

Checkpoint ID from a previous /convert request (with save_checkpoint=true). Skips re-parsing when provided.

page_schema
string | null

The JSON schema for structured extraction. Generate with Pydantic .model_dump_json() or write manually. Must contain a 'properties' key. Mutually exclusive with schema_id.

schema_id
string | null

ID of a saved extraction schema (e.g. sch_k8Hx9mP2nQ4v). Mutually exclusive with page_schema.

schema_version
integer | null

Version number of the schema to use. Only valid with schema_id. If omitted, the latest version is used.

mode
string | null

Output mode for parsing (only used when providing a file, not a checkpoint). Defaults to 'accurate' for balanced extraction and 'fast' otherwise.

max_pages
integer | null

The maximum number of pages to process.

page_range
string | null

The page range to process, comma separated like 0,5-10,20.

output_format
string | null

The output format for the parsed text alongside extraction results. Defaults to 'markdown'.

save_checkpoint
boolean
default:false

Save a checkpoint after processing for future extraction/segmentation calls.

skip_cache
boolean
default:false

Skip the cache and re-run.

webhook_url
string | null

Optional webhook URL to call when the request is complete.

processing_location
string | null

Optional residency region override (e.g. us, eu). When provided, use file_url or direct-upload; multipart uploads are rejected. When omitted, the request uses the team's configured residency and profile.

workflowstepdata_id
integer | null

Optional workflow step data ID to associate with this request.

extraction_mode
string | null

Extraction mode: 'turbo' (fastest; image-only, no OCR/citations/verification, returns JSON only), 'fast' (low latency and cost), or 'balanced' (highest accuracy with per-field verification, reasoning, and citations; slower). Defaults to 'balanced'.

model_override_settings
string | null
file
file | null

Input PDF, word document, powerpoint, or image file, uploaded as multipart form data. Images must be png, jpg, or webp format.

Response

Successful Response

request_id
string
required

The ID of the request. This ID can be used to check the status of the request.

request_check_url
string
required

The URL to check the status of the request and get results.

success
boolean
default:true

Whether the request was successful.

error
string | null

If the request was not successful, this will contain an error message.

versions

A dictionary of the versions of the libraries used in the request.