Pricing

from $0.01 / 1,000 results

Try for free

Go to Apify Store

PDF Intelligence - AI-Powered PDF Processing

Try for free

Intelligent PDF processor with automatic AI features. Extract text (with OCR for scans), tables, metadata, and RAG-ready chunks. Three modes: One Click, BYOK (your keys, 50% off), and MCP Server for Claude Desktop. Optimized for large documents with memory-efficient streaming.

Pricing

from $0.01 / 1,000 results

Rating

0.0

(0)

Developer

Marielise

Actor stats

Bookmarked

Total users

Monthly active users

16 days ago

Last modified

Categories

MCP servers

Developer tools

Run Mode

runMode

Optional

How to run: 'One Click' processes your PDF with platform AI (you pay PPE), 'BYOK' uses your API keys (50% savings), 'MCP Server' starts the server for Claude/MCP clients.

Type:string

Default:one-click

Options:

one-clickbyokmcp-server

PDF URL

pdfUrl

Optional

URL of the PDF to process. Works with any public PDF link.

Type:string

Example:

https://www.w3.org/WAI/WCAG21/Techniques/pdf/img/table-word.pdf

Or Paste Base64 Content

pdfContent

Optional

Alternative: paste base64-encoded PDF content if you don't have a URL.

Type:string

What do you want to do?

action

Optional

Choose what to extract from your PDF. All options use AI automatically when beneficial.

Type:string

Default:extract_text

Options:

extract_textextract_tablesget_metadatachunk_for_ragfull_analysis

Specific Pages (optional)

pages

Optional

Process only specific pages (1-indexed). Leave empty for all pages. For very large PDFs (300+ pages), consider processing in batches.

Type:integer[]

Max. items:500

Max Pages to Process

maxPages

Optional

Limit processing to first N pages. Useful for very large documents. Leave empty or 0 for no limit.

Type:integer

Minimum:0

Maximum:1000

Default:0

Table Format

outputFormat

Optional

Output format for tables (only for Extract Tables action)

Type:string

Default:json

Options:

jsoncsvmarkdown

Chunk Size

chunkSize

Optional

Target chunk size in characters (only for Chunk for RAG action)

Type:integer

Minimum:100

Maximum:10000

Default:1000

OpenAI API Key

openaiApiKey

Optional

Your OpenAI API key. Enables GPT-4 Vision for OCR and intelligent extraction.

Type:string

Anthropic API Key

anthropicApiKey

Optional

Your Anthropic API key. Enables Claude Vision for OCR and analysis.

Type:string

Google API Key

googleApiKey

Optional

Your Google API key for Gemini. Enables Gemini Vision for OCR.

Type:string

Preferred AI Provider

preferredProvider

Optional

Which AI to use first. Auto tries: OpenAI -> Anthropic -> Gemini.

Type:string

Default:auto

Options:

autoopenaianthropicgemini

Enable HTTP API

enableHttpApi

Optional

Enable REST API endpoint at /api for external integrations.

Type:boolean

Default:true

Debug Mode

debug

Optional

Enable verbose logging for troubleshooting.

Type:boolean

Default:false

PDF URL to Markdown, Tables & RAG Extractor

thescrapelab/Apify-PDF-url-scraper

Extract clean Markdown, page text, tables, metadata, summaries, and AI-ready RAG chunks from PDF URLs.

Inus Grobler

PDF Scraper

onidivo/pdf-scraper

Scrape and extract text from PDF links.

Onidivo Technologies

520

PDF AI Extractor MCP

devaditya/pdf-ai-extractor-mcp

Extracts text, tables, summaries, and structured data from any PDF using OpenAI, Google Gemini, or Claude. Supports bulk AI processing, clean JSON exports, and an AI-ready MCP mode for agent workflows.

lalithhh

Document Extractor API - AI-Powered PDF & Text Analysis

fresh_cliff/document-extractor-api

Extract text and data from PDF, Word, and image documents using AI-powered OCR. Convert documents to structured JSON, analyze content, and extract insights. No API keys required with mirror fallbacks.

Brennan Crawford

PDF to Markdown RAG-Ready

hedelka/pdf-to-markdown-rag

Premium PDF scraper that preserves tables and structure. Optimized for RAG.

Dmitry Goncharov

Pdf API

vivid_astronaut/pdf

BRAINIALL Team

Bulk Pdf To Json OCR

gagandeo/bulk-pdf-to-json-ocr

Convert PDF invoices, menus, images with text and documents into structured JSON. Features hybrid Digital+OCR parsing and AI-powered data extraction.

Kumar Gagandeo

PDF Text Extractor - Text, Metadata & Page Count from PDF URL

ninhothedev/pdf-text-extractor

$0.5/1K 🔥 PDF text extractor API! Extract full text, metadata & page count from any PDF URL — ready for RAG, LLMs & AI pipelines. No API key. Export JSON, CSV, Excel or API in seconds ⚡

ninhothedev

PDF Text Extractor MCP

reverberant_equality/mcp-pdf-extractor

Extract text and metadata from PDF URLs for AI agents, RAG pipelines, research workflows, legal documents, reports, and knowledge-base ingestion.

Jordan C

PDF Text & OCR Extractor — Scanned PDF to Text API

eliai/pdf-text-extractor

Extract the text from a PDF file. Born-digital or scanned PDFs by URL; OCR runs only when a PDF lacks a text layer. Bulk up to 50 files for RAG and document QA. $0.003 per parsed PDF today; failed URLs free.