Extract text (OCR)
Extract text from a document or image synchronously and get it back as per-page markdown. model and document are required; document is one of {type:"document_url", document_url}, {type:"image_url", image_url}, {type:"base64", content, document_name} (PDF or image), or {type:"file", file_id} for a file_<id> from POST /v3/files. pages selects 0-based page indices; include_image_base64/image_limit/image_min_size control embedded-image extraction; everything in parameters is forwarded verbatim to the provider (e.g. Docling’s ocr_engine, lang, table_mode, do_formula_enrichment). Billed per page processed.
file_id), and language options.Authorizations
API key authentication. Pass your API key as a Bearer token.