Iteration Layer
Document Extraction

Iteration Layer vs Nanonets

Nanonets offers schema-based extraction via open-source models — but typed fields, source citations, and EU hosting are missing.

No credit card required — start with free trial credits

Why developers switch from Nanonets

Nanonets uses open-source OCR models with generic schema definitions — not purpose-built typed fields.

17 typed fields vs. generic JSON Schema

Nanonets accepts a JSON schema but returns string values you still need to parse. We provide 17 purpose-built field types — dates as ISO dates, currencies as amount-plus-symbol objects, IBANs validated — with no post-processing needed.

Source citations on every field

Nanonets returns extracted values with no link back to the original document text. We return a verbatim source citation for every field, so you can audit and verify extraction results without re-reading the document.

EU hosting with GDPR compliance

Nanonets has no EU-only hosting option for their cloud API. 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 Nanonets
Schema-defined extraction
Yes

Define extraction fields via a purpose-built schema with 17 typed field types

Yes

Accepts a JSON schema for structured extraction via their DocStrange API

Typed field support
17 types

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

Generic types

JSON Schema primitive types only — extracted values are strings requiring manual type parsing

Confidence scores
Per field

Confidence score between 0 and 1 for every extracted schema field

Per field

Confidence scores provided per extracted field value

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 Office formats via their DocStrange parsing pipeline

MCP server
Yes

MCP server available for integration with AI agents and assistants

No

No MCP server available for AI agent integration

Open-source models
Proprietary

Closed-source managed SaaS platform

Open source

OCR models (Nanonets-OCR-s, OCR2) are open source on Hugging Face with self-hosted option

Self-hosted option
SaaS only

Available only as a managed SaaS platform

Yes

DocStrange library supports fully offline local processing via GPU or CPU

Free tier
Trial credits

Free trial credits for evaluation

10,000 free docs

One-time free cloud allowance of 10,000 documents plus unlimited self-hosted usage

EU hosting
EU only

All processing happens exclusively on EU-hosted servers

No

No EU-only hosting option for the cloud API

Language support
Any language

REST API callable from any programming language with HTTP support

Any language

REST API accessible from any programming language

Pricing model
Per page

Simple, predictable per-page pricing

Free + paid tiers

Free cloud tier with 10,000 docs/month, paid IDP platform billed per block execution

Infrastructure required
None

Fully managed API with no deployment or infrastructure to manage

Optional

Managed cloud API available, or self-hosted with GPU recommended for best performance

GDPR / Data privacy
Zero retention

No files or results stored beyond temporary 90-day logs

Self-host for privacy

Cloud API has no EU-only option — self-hosted mode available for data-sensitive use cases

Data used for training
Never

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

Enterprise only

Customer data is used for model training by default; opt-out requires an Enterprise contract ($100,000 minimum)

Pricing

Start with free trial credits. No credit card required.

Developer

For individuals & small projects

$29.99 /month
1,000 credits included
Most Popular

Startup

Save 40%

For growing teams

$119.99 /month
5,000 credits included

Business

Save 47%

For high-volume workloads

$319.99 /month
15,000 credits included

Or pay as you go from $0.022/credit with automatic volume discounts.

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. No credit card required.