Iteration Layer
Products
Use Cases
Resources
Pricing
Document Extraction

Iteration Layer vs Kreuzberg

Kreuzberg is a fast self-hosted extraction library — you trade zero per-doc cost for everything that comes with running your own infrastructure.

Why developers switch from Kreuzberg

Kreuzberg is fast and open source, but you own the deployment, scaling, and monitoring.

No infrastructure to run

Kreuzberg is a library you deploy, scale, monitor, and upgrade. Our API is a managed service — one HTTP endpoint, zero deployment overhead, and processing that scales automatically with your volume.

Schema-driven typed extraction

Kreuzberg extracts raw text. Getting a date, a currency amount, or an IBAN still requires parsing that text yourself. Our schema returns 17 typed fields — dates as ISO dates, currencies structured, IBANs validated — with confidence scores on every value.

Full pipeline, one platform

Kreuzberg does document extraction only. We offer document extraction, image transformation, image generation, document generation, and sheet generation — all under one API key, with a shared credit pool.

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 Kreuzberg
Schema-defined extraction
Yes

Define the fields you want in a schema and receive typed JSON results immediately

No

Outputs plain text or markdown without schema-based extraction

Typed field support
17 types

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

None

Raw text extraction only without typed field support

Confidence scores
Per field

Confidence score between 0 and 1 for every extracted schema field

No

No confidence scoring for extracted content

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 call 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 multiple extraction backends

Other APIs included
5 APIs

Document extraction, image transformation, image generation, document generation, and sheet generation under one API key

Extraction only

Focused on document text extraction with no other APIs included

Open source
Proprietary

Closed-source managed SaaS platform

MIT license

Free and open source under the MIT license with zero per-document cost

Raw throughput
Managed

Cloud-based processing with automatic scaling — no tuning required

Very fast

Rust-based engine that is 9x faster than Python alternatives for text extraction

EU hosting
EU only

All processing happens exclusively on EU-hosted servers

Your choice

Runs on your infrastructure, so data residency depends on where you deploy

Pricing model
Per credit

Pay-per-use pricing based on the number of extraction requests

Free

Open source and free to use — costs are limited to your own compute infrastructure

Infrastructure required
None

Fully managed API with no deployment, scaling, or maintenance required

Self-hosted

Requires deploying, scaling, and maintaining the Rust binary on your infrastructure

GDPR / Data privacy
Zero retention

No files or results stored beyond temporary 90-day logs

Self-hosted

Data never leaves your servers since the library runs entirely on your infrastructure

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