Question 1

How fast is 'fast'?

Accepted Answer

Kreuzberg is built on a high-performance Rust core, so most documents are processed almost instantly- in milliseconds instead of seconds. For bulk jobs that's thousands of pages per hour on a single API key.

Question 2

What file types do you support?

Accepted Answer

PDFs (native and scanned), images (JPG, PNG), Microsoft Office (DOCX, PPTX, XLSX), web content, and plain text. We detect document type automatically and optimize extraction for each format.

Question 3

Do you handle scanned documents?

Accepted Answer

Yes. Built-in OCR recognizes text in images and scanned PDFs. No additional configuration needed—just send the file and get structured output back.

Question 4

What happens to my documents?

Accepted Answer

Documents are processed in memory and deleted immediately after extraction. No storage, no indexing. We don't train on your data or use it for model improvement.

Question 5

What license does Kreuzberg use?

Accepted Answer

The Kreuzberg open-source library is licensed under the Elastic License v2 (ELv2) from v4.8.0 onward. You can use it freely for personal projects, internal tools, and commercial applications. The one restriction: you cannot offer Kreuzberg as a managed service to third parties. Versions v4.7.x and below remain MIT-licensed.
Kreuzberg Cloud is a separate commercial product with its own terms.
If you need a different licensing arrangement, [contact us](mailto:contact@kreuzberg.dev).

Question 6

I already use your open-source library with good results. Why should I try Kreuzberg cloud?

Accepted Answer

The open-source engine is fully usable and powerful on its own. Kreuzberg Cloud removes the operational complexity, so you can run it in production without worrying about managing infrastructure.

Framework	OCR SUPPORT	BATCH PROCESSING	ASYNC SUPPORT
Kreuzberg Markdown Baseline
Pandoc
Tika

Benchmarks

Benchmarks by language and file type

Processing Speed

Memory Usage

Duration

Quality Score

Success Rate

Cold Start

Installation Footprint

CPU Usage

Framework Capabilities

Download Benchmark Data

We value your privacy