For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Run OCR on an Base64 encoded image or PDF. This endpoint will return immediately and the OCR will be processed asynchronously.
Authentication
AuthorizationBearer
Bearer authentication of the form Bearer <token>, where token is your auth token.
Request
This endpoint expects an object.
mimeTypestringRequired
MIME type of the image. Supported types are image/png, image/jpeg, and application/pdf.
imagestringRequired
Base64 encoded image or PDF. PNG, JPG, WEBP, and PDF are supported. 10MB max.
vendorNetworkenumOptional
Limit OCR vendor search to a specific network
Allowed values:
entityIdstringOptional
When using the Entity vendor network, specify the entity to use. EntityId on an auth token will take precedence over this parameter.
splitDocumentbooleanOptional
If true, attempt to split the document into subdocuments before processing. Default is false. If a document is split into subdocuments, the linked OCR jobs will be accessible via the linkedJobIds field on each OCR job response.
