# Kreuzberg

> Document text extraction for AI pipelines. Extract text, tables, and metadata from PDFs, images, Office documents, and 92 file formats — plus 305 programming languages for code intelligence. Available as an open-source library (Rust core, 12 language SDKs) and as a managed cloud API.

Kreuzberg ships in two forms. The open-source library runs locally or in your own infrastructure under the Elastic License v2. Kreuzberg Cloud is a managed API at <https://kreuzberg.dev> with pay-as-you-go pricing ($0.008/page, first 10,000 pages free, no monthly minimum) and an Enterprise tier for 100K+ pages/month. Both share the same Rust extraction core; some advanced backends (vision-language-model OCR, custom embedding providers) are currently OSS-only.

The cloud API base URL is `https://api.kreuzberg.dev`. The flow is async: you submit documents, receive job IDs, and either receive an HMAC-SHA256-signed webhook with results or poll `GET /v1/jobs/{id}`. Authentication is bearer API key (`kbg_live_…`), issued from the dashboard.

## Platform

- [Landing page](https://kreuzberg.dev/): product overview, capabilities, pricing CTA
- [Capabilities](https://kreuzberg.dev/llms/capabilities.md): supported formats, OCR, layout detection, table extraction, code intelligence
- [Pricing](https://kreuzberg.dev/llms/pricing.md): three tiers (Open Source, Cloud Pay-as-you-go, Enterprise)
- [FAQ](https://kreuzberg.dev/llms/faq.md): speed, supported formats, scanned documents, data handling, licensing

## API

- [Extraction API overview](https://kreuzberg.dev/llms/api.md): public `/v1/extract`, presigned uploads, job polling, usage, error codes
- [Getting started](https://kreuzberg.dev/llms/getting-started.md): minimal curl, Python, and TypeScript examples against `POST /v1/extract`
- [Documentation site](https://docs.kreuzberg.dev/): full reference, SDK docs, integration guides
- OpenAPI spec: `https://api.kreuzberg.dev/api-doc/openapi.json` (live, generated from the running service)
- [Platform/management API](https://kreuzberg.dev/llms/platform-api.md): projects, API keys, members, webhooks, billing (dashboard backend)

## Open source

- [GitHub repository](https://github.com/kreuzberg-dev/kreuzberg): Rust core + 12 language bindings (Rust, Python, TypeScript, JavaScript, Node.js, PHP, Ruby, Elixir, Go, C#, R, WebAssembly)
- License: Elastic License v2 from v4.8.0 onward (free for personal, internal, and commercial use; no managed-service resale). Versions ≤ v4.7.x are MIT.

## Optional

- [Privacy policy](https://kreuzberg.dev/privacy)
- [Terms of service](https://kreuzberg.dev/terms)
- [Imprint](https://kreuzberg.dev/imprint)
- [Discord community](https://discord.gg/xt9WY3GnKR)
- [LinkedIn](https://www.linkedin.com/company/kreuzberg-dev/)
- Contact: <contact@kreuzberg.dev>