Iteration Layer
Products
Use Cases
Resources
Pricing
Document Extraction

Iteration Layer vs Reducto

Reducto is the closest competitor — the key differences are in schema ergonomics and extraction guarantees.

Why developers switch from Reducto

Reducto uses JSON Schema for field definitions — verbose compared to simple typed field declarations.

17 typed fields vs. JSON Schema

Reducto defines extraction schemas using JSON Schema — verbose, string-typed, without dedicated date, IBAN, currency, or address types. We provide 17 purpose-built field types that return validated, structured values without any post-processing.

Source citations on every field

Reducto does not return source citations linking each extracted value back to the original document text. We return verbatim citations for every field, so you can audit and verify extraction results.

EU hosting with GDPR compliance

Reducto is US-based. We process all documents on EU servers with zero data retention and a Data Processing Agreement available for every customer.

Feature-by-feature comparison

We went through the docs so you don't have to. Here's how every feature compares — including the ones where we're not the better choice.

Feature Iteration Layer Reducto
Schema-defined extraction
Yes

Simple, purpose-built schema with 17 typed field types that return validated structured values

JSON Schema

Uses standard JSON Schema with verbose syntax and string-based primitive types

Typed field support
17 types

Choose from 17 typed schema fields including date, IBAN, currency, address, phone, email, and URL

Primitives

JSON Schema primitives like string, number, and boolean without domain-specific types

Confidence scores
Per field

Confidence score between 0 and 1 for every extracted schema field

No

No confidence scoring for extracted values

Source citations
Yes

Verbatim source citation from the document for every extracted field

No

No source citation linking extracted values back to document text

Multi-file support
Up to 20 files

Process up to 20 files in a single API request with merged extraction results

1 file

Each API request processes a single file

Supported input formats
40+ formats

Process 40+ formats — PDF, Office, EPUB, RTF, LaTeX, email, Jupyter, images, and more — in a single API endpoint

PDF, images, Office

Supports PDF, images, and various document formats

MCP server
Yes

MCP server available for integration with AI agents and assistants

No

No MCP server available

RAG chunking
JSON output

Returns structured JSON which can be used in RAG pipelines but is not chunk-optimized

Built-in

Strong document chunking capabilities designed for RAG pipeline ingestion

Complex tables
Standard

Standard table extraction for common formats

Advanced

Good handling of multi-column layouts and complex table structures

Output flexibility
JSON only

Returns typed JSON matching the defined schema

Multiple formats

Supports markdown, structured chunks, and other flexible output formats

EU hosting
EU only

All processing happens exclusively on EU-hosted servers

US-based

Processing infrastructure is located in the United States

Pricing model
Per page

Simple, predictable per-page pricing

Per page

Per page processed with pay-as-you-go pricing and volume discounts

Infrastructure required
None

Fully managed API with no deployment or infrastructure to manage

None

Fully managed cloud API with no infrastructure to manage

GDPR / Data privacy
Zero retention

No files or results stored beyond temporary 90-day logs

US-based processing

Documents are processed through Reducto's managed API

Data used for training
Never

Your data is never used to train or improve AI models — guaranteed for all plans

Unclear

Public pages do not surface a no-training guarantee for customer data

Pricing

Start usage-based. Switch to a subscription when your volume becomes predictable.

Pay as you go

Usage-based

$0.033 to $0.022 / credit

Graduated pricing. Your effective rate decreases automatically as monthly usage grows.

  • No monthly commitment
  • Pay only for credits used
  • Automatic volume discounts as usage grows
Subscriptions

Predictable volume

From $29.99 /month

Fixed recurring credit packs with lower effective credit prices for steady usage.

  • Lower effective per-credit prices
  • Fixed recurring credit packs
  • Predictable monthly budget
All APIs included Free trial credits per API Project-based budget caps Auto overage billing

Still evaluating?

See how we compare — and where the competition still wins. Choosing the right tool shouldn't require a week of research.

Start building in minutes

Free trial credits included.

Zero data retention Made & hosted in the EU $65 free trial credits