PDF Vector

PricingFAQAPI Documentation
Get startedSign in

PDF to Markdown API for Developers

Convert any PDF to clean, structured markdown with our enterprise-grade document parser.

  • Battle-Tested Document Parsing – Convert PDFs to clean markdown, proven by Research Kick and ChatAcademia
  • Clean & Structured Data – Consistent formatting for both parsed documents and search results
  • Simple Integration – REST API or TypeScript SDK with comprehensive documentation and examples
Get StartedSign In

Trusted by

Research Kick

Research Kick

ChatAcademia

ChatAcademia

Document Parse API

API Docs
import { readFile } from "fs/promises";
import { PDFVector } from "pdfvector";

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

const urlResult = await client.parse({
  url: "https://arxiv.org/pdf/2506.04284",
  useLLM: "auto"
});

const fileResult = await client.parse({
  data: await readFile("document.pdf"),
  contentType: "application/pdf",
  useLLM: "auto"
});

Document Parsing Done Right

We're an independent team that doesn't need thousands of customers. Instead, we focus on making sure every customer gets reliable, accurate document parsing for both PDF and Word files.

Get started

Accurate Document Processing

Advanced parsing algorithms that handle complex PDFs and Word documents correctly. Preserves formatting, tables, images, and document structure with precision.

Production-Ready Performance

Built for scale and reliability. Fast processing times with consistent results across all document formats, trusted by applications serving thousands of users.

Battle-Tested Reliability

Proven in production by document-heavy products like Research Kick and ChatAcademia. Handles edge cases and diverse document types with confidence.

Fair & Transparent Pricing

Straightforward pricing that scales with your needs. Same pricing for both PDF and Word documents - no hidden fees, no surprises.

Example Output

Watch how our API transforms complex PDF documents into clean, structured markdown

Original Document

With table

Parsed Markdown

Clean, structured output

Example table

This is an example of a data table.

|  Disability
Category | Participants | Ballots
Completed | Ballots
Incomplete/
Terminated | Results |   |
| --- | --- | --- | --- | --- | --- |
|   |  |  |  | Accuracy | Time to
complete  |
|  Blind | 5 | 1 | 4 | $34.5 \%, n=1$ | 1199 sec, $n=1$  |
|  Low Vision | 5 | 2 | 3 | $98.3 \% n=2$ | 1716 sec, $n=3$  |
|   |  |  |  | $(97.7 \%, n=3)$ | $(1934 \mathrm{sec}, n=2)$  |
|  Dexterity | 5 | 4 | 1 | $98.3 \%, n=4$ | 1672.1 sec, $n=4$  |
|  Mobility | 3 | 3 | 0 | $95.4 \%, n=3$ | 1416 sec, $n=3$  |

One subscription, all APIs

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

Save one month

Free

$0

Credit Card Required

Perfect for testing and small projects

  • Access to all APIs
  • 100 credits
  • LLM parsing
Subscribe to Free

Basic

$15/month

$176 billed annually

Great for personal projects and small businesses

  • Access to all APIs
  • 3,000 credits
  • LLM parsing
Subscribe to Basic
Most Popular

Pro

$72/month

$869 billed annually

Most popular plan for growing businesses

  • Access to all APIs
  • 100,000 credits
  • LLM parsing
Subscribe to Pro

Enterprise

$305/month

$3663 billed annually

For large-scale applications and enterprises

  • Access to all APIs
  • 500,000 credits
  • LLM parsing
Subscribe to Enterprise

Ready for Reliable PDF Parsing?

Join the developers who trust PDF Vector for accurate, consistent PDF parsing. Battle-tested reliability with simple integration - start building with confidence today.

Get started nowSign in

No setup fees • Integrate in minutes • Cancel anytime

Frequently asked questions