Free if you’re curious, custom if you’re serious.

All your data — the messiest, the most difficult, the real-time — transformed with human-level accuracy. We get your data LLM-ready.

Let's Go

Start processing your data with 10,000 free pages.

Free

Get Started

Includes

• 10,000 free pages to start.
• No card required.
• All features included.

Pay-As-You-Go

Pay only $0.015 a page after your first 10,000 free pages.

$0.015

/ page

Pay-As-You-Go

Includes

• 10,000 free pages when your account starts.
• Charge $0.015 per page after the first 10,000 pages.
• All features included.

Business

Built for teams of any size that need privacy, control, and security. Deploy Unstructured in your own dedicated instance or VPC with multi-user access, full data isolation, dedicated technical support, and pricing tailored to your needs.

Custom
Contact Sales

Includes

• Custom Pricing.
• Multi-user accounts.
• All Features.
• Dedicated Instance, VPC or Multi-Tenant SaaS.

All Plans Include

Powerful features, limitless possibilities.

However you choose to deploy, Unstructured gets your documents clean, structured, and ready for GenAI at scale.

Hosting & Deployment

Hosting

Included

• Unstructured
• AWS Marketplace
• Azure Marketplace

Deployment Options

Included

• SaaS Cloud-Hosted
• Dedicated Instance*
• In-VPC (Azure, AWS or GCP)*
• Bare Metal*

*Business Plan Only

Extract

Extract Features

Included

• 40+ Connectors
• 20+ Sources
• 20+ Destinations
• 10+ VLMs
• Multi-source or Destination Configuration Options
• 24/7 Connector Maintenance
• Change Detection Intelligence
• Event-driven Updating
• Incremental Processing
• Opinionated Writing*
• Batch Data Processing

*Preview Connectors

Source Connectors

Included

• Airtable*Enabled On Request
• Astra DB*Enabled On Request
• Azure Blob Storage
• Box
• Confluence
• Couchbase
• Databricks Volumes
• Discord*Enabled On Request
• Dropbox
• Elasticsearch
• GitHub*Enabled On Request
• GitLab*Enabled On Request
• Google Cloud Storage
• Google Drive
• Jira
• Kafka
• Local File System*Enabled On Request
• MongoDB
• Notion*Enabled On Request
• OneDrive
• OpenSearch*Enabled On Request
• Outlook
• PostgreSQL
• S3
• Salesforce
• SFTP*Enabled On Request
• SharePoint
• SingleStore*Enabled On Request
• Slack
• Snowflake
• SQLite*Enabled On Request
• VastDB*Enabled On Request
• Zendesk

*Preview Connectors

Transform

Transform Features

Included

• 50+ Document and Image File Types
• Rich Metadata Out of the Box
• Auto / VLM / High-Res / Fast Transformation Strategies
• Generative OCR Enrichment
• Image Description Enrichment
• Table Description Enrichment
• Structured Data Extraction Coming Soon
• Named Entity Recognition Enrichment
• Custom Models for Document Hierarchy and Element Classification
• 3rd-Party Model Integration
• Embedding Generation
• Support for Unstructured and Structured Data
• Schema Evolution
• Full Transformation Pipeline: Partition, Chunk, Enrich, Embed
• Custom Enrichments (VPC ONLY)
• Data Normalization/Flattening
• Reading Order Detection

Files Supported (45+)

Included

• .ABW
• .BMP
• .CSV
• .CWK
• .DBF
• .DIF
• .DOC
• .DOCX
• .DOT
• .EML
• .EPUB
• .ET
• .ETH
• .FODS
• .HEIC
• .HTM
• .HTML
• .HWP
• .JPEG
• .JPG
• .MCW
• .MD
• .MSG
• .MW
• .ODT
• .ORG
• .P7S
• .PBD
• .PDF
• .PNG
• .POT
• .PPT
• .PPTM
• .PPTX
• .PRN
• .RST
• .RTF
• .SDP
• .SXG
• .TIF
• .TIFF
• .TXT
• .TSV
• .XLS
• .XLSX
• .XML
• .ZABW

Partition

Partition Strategies

Included

• Auto
• Fast
• High-Res
• VLM

Chunk

Chunking Strategies

Included

• Chunk by Character
• Chunk by Title
• Chunk by Page
• Chunk by Similarity
• Contextual Chunking

Enrich

Enrichment

Included

• Metadata Extraction
• Named Entity Recognition (NER)
• Generative OCR
• Image Description
• Table Description
• Table to HTML

Embed

Embedding Options

Included

• Azure OpenAI: text-embedding-3-small
• Azure OpenAI: text-embedding-3-large
• Azure OpenAI: Ada 002
• IBM: All Minilm L6 2
• IBM: Granite Embedding 107m Multilingual
• IBM: Granite Embedding 278m Multilingual
• IBM: Multilingual E5 Large
• IBM: Slate 125m English Rtrvr
• IBM: Slate 125m English Rtrvr V2
• TogetherAI: M2-BERT-80M-32K-Retrieval
• Bedrock: Titan Text Embeddings V2
• Bedrock: Titan Embeddings G1 - Text
• Bedrock: Titan Multimodal Embeddings G1
• Bedrock: Cohere Embed English
• Bedrock: Cohere Embed Multilingual
• VoyageAI: voyage-code-2
• VoyageAI: voyage-3
• VoyageAI: voyage-3-large
• VoyageAI: voyage-3-lite
• VoyageAI: voyage-code-3
• VoyageAI: voyage-finance-2
• VoyageAI: voyage-law-2
• VoyageAI: voyage-multimodal-3

Partner Integrations

Integrations

Included

• Amazon Bedrock
• Anthropic Claude
• Azure AI Studio
• IBM watsonx
• Gemini
• Open AI
• NVIDIA
• Together.ai
• VertexAI

Load

Load Overview

Included

• 20+ Destinations

Destination Connectors

Included

• Astra DB
• AWS Delta Table
• Azure Blob Storage*Enabled on Request
• Azure AI Search
• Chroma*Enabled on Request
• Couchbase
• Databricks Delta Tables (Mosaic)
• Databricks Volumes
• Dropbox*Enabled on Request
• DuckDB
• Elasticsearch
• Google Cloud Storage
• IBM Milvus
• IBM watsonx.data
• Kafka
• KDB.AI*Enabled on Request
• LanceDB*Enabled on Request
• MongoDB
• Neo4j
• OneDrive
• OpenSearch*Enabled on Request
• Pinecone
• PostgreSQL
• Qdrant
• Redis
• S3
• SingleStore*Enabled On Request
• Snowflake
• VastDB*Enabled On Request
• Vectara*Enabled On Request
• Weaviate

*Preview Connectors

Plus+

Features

Included

• Full ETL Orchestration
• Smart Document Routing
• Workflow Optimization
• Workflow Scheduling
• Role-Based Access Control
• Custom Plugins for Specialized Pipelines In-VPC Only
• Custom Model Hosting for LLMs/VLMS/Embedding Models In-VPC Only
• 24/7 Connector Maintenance
• Multi-Source Configuration
• Compliance with HIPPA, SOC2 Type 2, GDPR Compliance, ISO 27001, +More
• Workflow Management
• Data Duplicate Prevention
• Change Detection Intelligence
• Opinionated Writing
• Metadata Propagation
• Retry Mechanisms
• Error Transparency
• Quick and Easy Configuration after connectors are set up

Security

Data Security

Included

• Data Only Processed Within Your Company's Dedicated Infrastructure
• Permission-Based Access (Roled-Based Access Control: RBAC)
• Secure Connector Authentication Credentials Handling
• Data is Encrypted in Transit
• Zero Data Retention

Compliance

Compliance

Included

• HIPAA Compliant
• SOC 2 Type 2
• GDPR Compliant SaaS Hosted Product
• ISO 27001

Support

Customer Support

Included

• Slack Community
• Personal Support Representative
• Email support@unstructured.io

Unstructured has solved the most difficult part of building an LLM application: working with data.

FAQs

Most common questions. If you have any further questions please contact us here.

I like using your open source software. Why should I try Unstructured?

What kinds of documents can I process with Unstructured?

How do I know my data is secure?

What if I need help getting started?

Ready for a demo?

See how Unstructured simplifies data workflows, reduces engineering effort, and scales effortlessly. Get a live demo today.

Contact Sales