Convert a document to Markdown (MarkItDown)
From the API's own job list: GET https://api.gaents.com/v1/jobs answered HTTP 200 at 2026-11-19T06:07:32Z. Not a live reading: call it for the state now.
One document (PDF with a text layer, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, EPUB; base64) in, Markdown out. Scanned PDFs without a text layer come back empty (not charged): OCR them page by page with ocr-tesseract.
Call it
curl -s https://api.gaents.com/v1/jobs/doc-to-markdown -H "Authorization: Bearer $GAENTS_KEY" -H 'Content-Type: application/json' \
-d "{\"file_b64\": \"$(base64 -w0 YOUR_FILE)\", \"filename\": \"YOUR_FILE\"}"
Get a key on the start page or in the dashboard. MCP tool: job_doc_to_markdown. Doors: bearer, x402, mcp.
- Unit
- call
- Charged
- measured CPU seconds of this call x our compute cost, by the 60% rule; never above the quote; no charge for an empty result or a failed run
- Price ceiling
- $0.00006268 per call (the API's
price_ceiling_usd) - Runs so far
- 1 (1 ok, 1 buyers)
- Runs
- Microsoft MarkItDown (source); licence: MIT
- In Proven
- MarkItDown (Microsoft) (item
94ed0b028b9b3481)
Parameters
file_b64(base64, required): the document, base64filename(string, required; max 120 chars): its file name; the extension picks the converter