Get 10k free credits when you signup for LlamaParse!

Document OCR for the agentic stack

LlamaParse turns hours of manual document processing into seconds of automation, with VLM-powered document understanding agents.

Get started with LlamaParse for free

Our free plan includes:

  • 10,000 free credits per month (~1000 pages)

  • Agentic OCR for layout-aware document parsing

  • Structured extraction of defined schemas

  • Build and deploy end-to-end document agents

How it works

We parse your most complex docs

/ /

Agentic Understanding

Complex layouts turned into clean, LLM-ready outputs through semantic understanding.

Specialized experts

Task-specific agents break down content such as text, charts, tables, and more, routing it to the right expert.

Auto-Correction Loops

Recursive checks that detect and fix errors automatically, delivering high pass-through rates even on messy scans and multi-modal documents.

Handwritten Text

Parse messy handwriting, extract structure, and make it usable for AI workflows.

Tables

Extract rows, columns, and relationships — even from dense or irregular layouts.

Charts

Turn charts and graphs into structured data your pipelines can use.

  • 1B+

    Documents processed

  • 25M+

    package downloads a month

  • 300k+

    LlamaParse users

Unrivaled performance across complex documents

Benchmark

  • LlamaParse

  • VLM - Proprietary

  • Commercial - IDP

  • Open Source OCR

01

LlamaParse

LlamaParse powers enterprise-grade document automation with industry-best parsing, extraction, indexing, and retrieval — optimized for accuracy, configurability, and scalability.

Parse

Industry-leading document parsing for 50+ unstructured file types — including support for embedded images, complex layouts, multi-page tables, and even handwritten notes.

Extract

Turn unstructured content into structured insights using schema-based, LLM-powered extraction agents — no training required

Split

Segment a document into logical sections based on natural-language descriptions.

Classify

Automatically categorize documents using natural-language rules.

Index

Enterprise-grade chunking and embedding pipeline. Built to deliver precision and relevance in every retrieval call for best-in-class RAG.

npm install @llamaindex/liteparse

02

LiteParse

Parse Any Document. Locally. Fast.

Open-source document parsing from the team behind LlamaParse. Parsed text from PDFs, Office docs, and images — no cloud, no LLM tokens, no limits.

Fully open-source

Fast local processing

All major formats

Bounding box output

Use cases

How leading teams use document intelligence

Context for AI Agents

Enable LLMs to read complex documents with human-level precision.

Book a demo

Replace legacy IDP

Modernize document processing without 
custom templates.

Book a demo

Multi-step document agents

Build durable agents that automate knowledge work.

Book a demo

Industries

Built for every document-heavy industry

Finance

From financial research and due diligence to automated invoice processing, leading banks, hedge funds, and fintechs are transforming workflows with AI.

Explore finance

Insurance

Risk and protection leaders are turning unstructured data into action—streamlining underwriting, audits, and claim proccessing.

Explore insurance

Manufacturing

Leading manufacturers are using AI to extract insights from specs, manuals, and inspection reports—faster and more accurately.

Explore Manufacturing

Healthcare

From medical records and handwritten doctor notes to insurance claims, healthcare providers are using AI to streamline clinical and administrative workflows.

Explore Healthcare

99.9% uptime

Infrastructure designed for always-on document processing — stable under real production load.

Enterprise-Grade Security

Granular access controls, enhanced data encryption, and HIPAA, GDPR, and SOC2 compliant out-of-the-box.

Dedicated Support & SLAs

Dedicated support, fast response times, and SLAs tailored to mission-critical AI workloads.

Flexible Deployment

Run in our secure cloud or deploy fully in your VPC, ensuring data residence requirements.

Enterprise Ready

Built for teams running production-grade AI
with reliability, security, and control at scale.

99.9% uptime

Infrastructure designed for always-on document processing — stable under real production load.

Enterprise-Grade Security

Granular access controls, enhanced data encryption, and HIPAA, GDPR, and SOC2 compliant out-of-the-box.

Dedicated Support & SLAs

Dedicated support, fast response times, and SLAs tailored to mission-critical AI workloads.

Flexible Deployment

Run in our secure cloud or deploy fully in your VPC, ensuring data residence requirements.

testimonials

Trusted by leading AI teams

Manuel De Juan

Director, Global AI office at NttData

“LlamaParse simplifies parsing complex documents which is crucial for end-to-end AI development.”

Alvin Alaphat

Founding engineer at Delphi

“We benchmarked LlamaParse against everything else we could find. It had the most reliable output and cleanest formatting—especially for our most difficult content.”

Dean Barr

Applied AI Lead and Data Scientist at Carlyle

“LlamaParse stands out as the premier solution for parsing complex documents in enterprise agent pipelines.”

Upgrade your document processing today

LlamaParse unlocks unrivaled accuracy and scale.