Unsiloed Extract
Schema-based extraction API: a PDF and a JSON Schema go to the /v2/extract endpoint and typed JSON comes back with a confidence score on every field and optional source-page citations, plus a beta mode that computes values not printed on the page from the ones that are; billed per page processed, with a free tier and custom plans.
Find alternatives to Unsiloed Extract
What it does
- Document extraction
Sources
- Pricing
-
Official documentation · 19 Oct 2026
FAQ "How is Extract priced?": "Pricing is based on pages processed, with a free tier and custom plans for higher-volume extraction and enterprise requirements."
- Description
-
Official documentation · 19 Oct 2026
"Extract takes a PDF and valid JSON Schema, then returns values that follow the requested structure. Each field includes a confidence score, and optional citations link values to their location in the source PDF."
- What it does
-
Official documentation · 19 Oct 2026
"Extract takes a PDF and valid JSON Schema, then returns values that follow the requested structure."
- Sold within
-
The page says it "uses the same authentication and billing as every other capability" and can be used "on its own", but names no plan that includes it or add-on price, and the pricing page lists plans by pages processed without naming this product.
- Name
-
Official documentation · 19 Oct 2026
Page title: "Extract: Schema-based data extraction from PDFs | Unsiloed AI"; heading "Define a schema, get typed JSON back."
- URL
-
Official documentation · 19 Oct 2026
The product's own page on unsiloed.ai, linked from its Product menu.
- Deployment
-
Official documentation · 19 Oct 2026
FAQ: "Managed, VPC, on-premises, and air-gapped deployment options are available."
- Interfaces
-
Official documentation · 19 Oct 2026
Page: "POST pdf_file and schema_data to /v2/extract with your api-key header".
- Modalities
-
Official documentation · 19 Oct 2026
Page: "Send a PDF and JSON Schema to /v2/extract to receive schema-shaped values with a confidence score on each field." in and out.
- Intended for
-
Official documentation · 19 Oct 2026
"Teams automating invoices, contracts, claims, and onboarding workflows that need consistent fields from documents with varied layouts."
Also from Unsiloed AI
-
Unsiloed AI API service
Document AI platform behind the Parse, Extract, Classify and Split endpoints: converts PDFs, images, Word, Excel, PowerPoint and scans into JSON, Markdown, structured tables, key-value pairs and layout output through a REST API and a Studio dashboard; a Free tier of 2,000 pages, Standard at $250 a month for 20,000 pages, extra pages billed per page, and a custom Enterprise tier with VPC, on-premises or air-gapped deployment.
-
Unsiloed Parse API service
Document parsing API: PDFs, images, Word and PowerPoint files go to the /parse endpoint (spreadsheets to /parse/excel) and come back as ordered Markdown chunks with tables, figures, headings, reading order and word-level source coordinates, with vision OCR for scans, faxes and photos; billed per page processed, with a free tier and custom plans for higher volume.
Open Unsiloed AI in the directory
Something wrong here? Send a correction — quote this product id: unsiloed-extract.