Redaction
Remove information from a PDF or image according to a redaction spec. The generated PDF is returned when available, including when verification checks fail. Inspect verdict and failing_checks before using it. Completed runs are charged even when verification fails. The report provides counts and check identifiers, without removed text.
Authorizations
Body
Optional file URL (http/https). If provided, the server will download and process it.
A built-in spec: 'personal_information' removes a private individual's identifiers; 'financial_details' removes account identifiers and payment credentials, including business accounts; 'business_confidentiality' removes counterparties, commercial terms and explicitly non-public information; 'manuscript_anonymisation' prepares a manuscript for double-blind review. Combined with redaction_spec, the spec's fields replace the preset's.
Optional JSON spec: {"goal": "...", "rules": [{"id", "label", "detail"}], "keep": [{"id", "label", "detail"}]}. "rules" says what to remove, "keep" what must stay.
Not supported for redaction. Omit this field; the whole document is reviewed (up to 60 pages).
Skip the cache and re-run the inference. Defaults to False.
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.
Input PDF, word document, powerpoint, or image file, uploaded as multipart form data. Images must be png, jpg, or webp format.
Response
Successful Response
The ID of the request. This ID can be used to check the status of the request.
The URL to check the status of the request and get results.
Whether the request was successful.
If the request was not successful, this will contain an error message.
A dictionary of the versions of the libraries used in the request.
True when this run automatically reused a checkpoint from a previous run of the same file, so the conversion step is not re-billed. Absent/None otherwise.