PDF VectorPDF Vector

Academic Parse

Convert paper IDs and provider URLs to markdown

  • Accepts DOI, PubMed, arXiv, Semantic Scholar IDs, and provider URLs
  • Finds the public PDF URL before parsing
  • Returns clean markdown plus paper metadata and credit usage

Academic Parse

Available as an action in

Maken8nZapier
PubMedarXivOpenAlexSemantic ScholarEurope PMCERICGoogle Scholar

Automate in 3 Steps

1

Pick Your Platform

Choose Make, n8n, or Zapier

2

Add PDF Vector

Search for 'PDF Vector' in apps/nodes list

3

Build Your Workflow

Connect to 1000+ apps

Popular Automations

Ready-to-use workflow templates for Make, n8n, and Zapier

Paper URL → Literature review notes

TriggerNew arXiv, PubMed, or Semantic Scholar URL added to a sheet
PDF Vector
OutputStore markdown, PDF URL, and metadata in a research database
maken8nzapier

DOI queue → RAG ingestion

TriggerNew DOI or paper ID arrives from a webhook
PDF Vector
OutputPush parsed markdown into a vector database pipeline
maken8nzapier

Research alert → Paper summary prep

TriggerWeekly paper alert returns candidate IDs
PDF Vector
OutputAttach markdown source text for downstream summarization
maken8n

For Developers

Get started in seconds. Copy and run.

import { createClient } from "@pdfvector/client";const client = createClient({ apiKey: "YOUR_API_KEY" });const result = await client.academic.parse({  id: "1706.03762",  model: "auto",});console.log(result.title);console.log(result.pdfURL);console.log(result.markdown);

Key Features

Paper-to-Markdown

Resolves a paper identifier or provider URL, fetches the public PDF, and parses it into structured markdown.

Provider URL Support

Use arXiv, PubMed, Semantic Scholar, and other academic URLs without first extracting an identifier yourself.

Clear Failure States

Returns explicit errors when the paper is not found, has no public PDF, or the resolved PDF cannot be fetched.

Credit Costs

Pick the model tier that fits your use case

Nano

Fast text extraction for simple PDFs and Word docs. No image support.

1 credits/page
Max pages30
Max file size40 MB

Mini

Handles tables and multi-column layouts. Good for structured reports.

2 credits/page
Max pages30
Max file size40 MB

Pro

Supports scanned documents, handwriting recognition, and complex layouts.

4 credits/page
Max pages30
Max file size40 MB

Max

Maximum accuracy for complex layouts. Returns HTML output.

8 credits/page
Max pages2000
Max file size500 MB

Everything You Need for Document Processing

Parse, ask questions, and extract structured data from any document type

Frequently Asked Questions

Start Processing Documents Today

Get 100 free credits to try all our APIs. No credit card required.

Free forever tier · No credit card · Cancel anytime