Unsiloed AI

unreachable

Unsiloed AI turns PDFs, Word documents, scans, images, slide decks and spreadsheets into structured output for language models and agents. Other formats are converted to PDF before submission. Parse returns a document as ordered Markdown and HTML chunks with segment types, bounding boxes, OCR text and confidence scores. Extract pulls the fields named in a JSON Schema out of a PDF, with a…

AIBasex402 v2exactagents.unsiloed.ai ↗︎

Not seen in any discovery source since 2026-11-12.

Transactions · 30d
0
Volume · 30d
$0.00
Unique buyers · 30d
0
Uptime · 30d
58.3%
Latency p50
670ms
Reported calls · 30d
5

Endpoints (6 live)

  • POST /classify — Creates a classification job for a PDF or image (JPG, PNG, GIF, WebP, BMP, TIFF) given by URL, with the list of candidate category names, and returns the job id at once. Poll GET /classify/{job_id} for the dominant category, its confidence, every category present with the pages that voted for it, and per-page results. Documents longer than four pages are classified from their first four. Usage is the page count of the document. (0.02 USDC on Base)
  • POST /v2/extract — Creates an extraction job for a PDF given by URL, with a JSON Schema of the fields to pull out, and returns the job id at once. Poll GET /extract/{job_id} for the typed values, each with a confidence score and, when citations are on, the page and bounding box it came from. Model tiers trade speed for thoroughness; high_accuracy_mode adds a verification pass. Usage is the page count of the PDF. (0.02 USDC on Base)
  • POST /parse — Creates a parse job for a PDF, DOCX, JPEG, PNG, WEBP or PPTX document sent by URL, and returns the job id at once. Other formats are converted to PDF first. Poll GET /parse/{job_id} for the ordered chunks with Markdown, HTML, OCR text, bounding boxes and confidence per segment. Options select the layout model, OCR engine, page range, output fields and exports. Excel workbooks go to POST /parse/excel. Usage is the page count of the document. (0.02 USDC on Base)
  • POST /splitter — Creates a splitting job for a PDF given by URL, with the categories to split into (names and optional descriptions), and returns the job id at once. Every page is classified and the pages of each category go to their own PDF; categories matching no page produce no file. Poll GET /splitter/{job_id} for the files with download links and confidence scores. enable_reordering restores logical page order. Usage is the page count of the PDF. (0.02 USDC on Base)
  • POST /zeroclick/agent/quote — Free Unsiloed AI seller advisor: API contracts, prices and purchase steps. No purchase is executed. (0 USDC on Base)
  • POST /parse/excel — Creates a parse job for an XLS or XLSX workbook given by URL, and returns the job id at once. Poll GET /parse/{job_id} for the result: every detected table as a segment with cell-range references back to the sheet, large tables split into row blocks. Options drop hidden sheets, rows, columns, styling and images and tune table detection. Usage is the page count of the workbook, where 5,000 by 5,000 cells count as one page. (0.02 USDC on Base)

First seen · last seen