Upload a reference file (PDF/DOCX/image) for the AI to query while editing.
Files are processed asynchronously and become AI-searchable once ready. The AI can then reference the attachment’s content during chat (e.g., “rewrite section 3 to match the style guide PDF I attached”). Images are queryable via multimodal vision. Poll get_attachment_status to know when ready. Distinct from upload_document_base64: attachments are read-only context for the AI to reference, not the editable working document. Supported formats: .pdf, .docx, .txt, .rtf, .md, .html, .htm. Max 50 MB validated; note the hosted transport layer caps any REQUEST BODY at ~32 MB and rejects larger ones at the gateway with an HTML (not JSON) error — base64 inflates content ~33%, so inline uploads are reliable up to ~20 MB of file bytes; beyond that use request_upload_url (pre-signed flow, up to 100 MB). Requires session_id.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
Body
JSON request body for base64-encoded file uploads.
Original filename with extension (e.g. 'contract.pdf'). Used for file type detection.
512Base64-encoded file content.
50000000Session ID. Auto-generated if not provided.
256With a session_id: false (default) returns compact metadata only (chunks_count, version_id, page_setup) — the document is loaded into the session and you edit it via chat, keeping your context small; true returns the full parsed HTML inline. Ignored on the convert-only path (no session_id), which always returns the converted html.
Response
Successful Response

