PDF Extraction API for developers

Extract structured data from PDF documents using AI and JSON Schema. Perfect for invoices, forms, research papers, and more.

Schema-Driven Extraction – Define your data structure with JSON Schema and get perfectly formatted results every time
AI-Powered Understanding – Advanced AI analyzes documents to extract exactly the data you need, handling variations gracefully
Type-Safe Integration – JSON Schema validation ensures consistent, predictable data structure for your applications

Get Started Sign In

Trusted by

Research Kick

ChatAcademia

ReadBack

RabbitHoles

Easy to use APIs

Use our simple APIs directly or our TypeScript SDK with just a few lines of code.

PDF Extract

API Docs

import { PDFVector } from "pdfvector";

const client = new PDFVector({
  apiKey: "pdfvector_xxxxxxx"
});

// From URL
const results = await client.extract({
  url: "https://example.com/invoice.pdf",
  prompt: "Extract all invoice details",
  schema: {
    type: "object",
    properties: {
      invoiceNumber: { type: "string" },
      date: { type: "string" },
      totalAmount: { type: "number" }
  }
  }
});

// From file
import { readFile } from "fs/promises";
const results = await client.extract({
  data: await readFile("document.pdf"),
  contentType: "application/pdf",
  prompt: "Extract all invoice details",
  schema: {
    type: "object",
    properties: {
      invoiceNumber: { type: "string" },
      date: { type: "string" },
      totalAmount: { type: "number" }
  }
  }
});

Response:

What people are saying

See how PDF Vector is helping teams improve their document processing workflows

“Can't recommend PDF Vector enough! It boosts your AI workflow accuracy to 100% while dropping your costs! Especially if you're a T4 Org in the $150/m spend range!”

— Abdo El-Mobayad

“Gotta give a shoutout to PDF Vector team for helping me set up PDF Vector for a project. They even delivered on a feature request before I purchased. Incredible customer service. 👏”

— Trent

“Been implementing RAG and changing a lot of things under the hood for @rabbitholesai, came across PDF Vector and it was a huge time saver. I got a document parsing solution for the rag pipeline within minutes! one less thing to worry about”

— Praneeth Pike

Example Output

Real examples of structured data extracted from PDFs

Original Document

Invoice

Output

AI-generated answer to your question

Question

Extract all invoice details

Schema

{
  "type": "object",
  "properties": {
    "invoiceNumber": {
      "type": "string"
    },
    "totalAmount": {
      "type": "number"
    },
    "Basic Fee wmView": {
      "type": "string"
    }
  },
  "required": [
    "invoiceNumber",
    "totalAmount"
  ],
  "additionalProperties": false
}

Answer

{
  "data": {
    "invoiceNumber": "123100401",
    "totalAmount": 453.53,
    "Basic Fee wmView": "130,00 €"
  },
  "pageCount": 3,
  "creditCount": 9
}

One subscription, all APIs

Start for free, then scale as you grow. No hidden fees.

Monthly

Annual

Save one month

Free

Credit Card Required

Perfect for testing and small projects

Access to all APIs
100 credits

Subscribe to Free

Basic

$23/month

$275 billed annually

Great for personal projects and small businesses

Access to all APIs
3,000 credits

Subscribe to Basic

PDF Extraction API for developers

Easy to use APIs

What people are saying

Structured Data Extraction

Example Output

One subscription, all APIs

Ready to Extract Data at Scale?

Everything you need for document processing

Frequently asked questions