Launch Promo: First 100 subscribers get Pro Plan at $29 $19/month 🎉
The fastest way to run Docling

Docling, as an API.

Run Docling on the cloud to convert PDFs, DOCX, PPTX, images, and more into Markdown or JSON. Just works, straight into your RAG or LLM pipeline.

Secure & Managed
GPU-Accelerated

Checking server status...

Integrate in One Line

Turn any document into Markdown with a single API call—no SDKs, no dependencies, no setup.

bash
# Convert a PDF to Markdown
$ curl -X POST https://api.rundocling.com/v1/convert/file \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "[email protected]" \
-F "to_formats=md"

How It Works

From raw files to RAG-ready output in three simple steps.

01Upload
Send PDFs, DOCX, PPTX, XLSX, HTML, or images to a single endpoint. Scanned contracts, dense reports, complex tables, we handle them all as-is.
02Process
Our GPU pipeline runs OCR, layout analysis, and table extraction under the hood, powered by IBM's Docling models for high-fidelity structure.
03Receive
Get clean Markdown or JSON with preserved headings, lists, tables, and metadata. Ready to drop straight into your RAG or LLM workflows.

Speed Matters

Processing time for a 10-page complex PDF with CAD drawings

M3 MacBook Pro87s
RunDocling20s

* Standard settings: OCR + Layout Analysis + JSON output. VLM-ready.

Why Docling?

The most advanced open-source document parsing library.

Any Document
PDF, DOCX, PPTX, XLSX, images, HTML. Handle them all through a single, simple API. No separate pipelines, no special cases.
Perfect Tables
Complex tables with merged cells, missing borders, or multi-row headers stay intact, so you can trust the numbers and layout you extract.
Scanned? No Problem
Built-in OCR automatically converts scanned PDFs and images into searchable text, with no extra services or manual preprocessing.
Structure Preserved
Headings, paragraphs, lists, and reading order are all maintained, giving you clean document structure instead of a flat text dump.
RAG-Ready Output
Exports clean Markdown or JSON that drops straight into LangChain, LlamaIndex, or your existing RAG stack without custom parsing.
Fast Processing
GPU-accelerated conversion delivers results in roughly sub-second per page, so you can process large batches without slowing users down.

Docling is powered by PyTorch and specialized ML models. We run it on GPU infrastructure so you don't have to.

Pricing

Start free, scale as you grow.

placeholder
Free
$0
Perfect for trying things out
  • 50 pages/month
  • All file formats
  • 20 pages/req, 20MB max
  • 1 concurrent request
  • Community support
Most Popular · Launching Promo 🎉
Pro
$29$19/month
For serious developers and teams
  • 10,000 pages/month, then $0.01/page
  • All file formats
  • 400 pages/req, 200MB max
  • 20 concurrent requests
  • Email support
placeholder
Enterprise
Custom
For large-scale deployments
  • Unlimited pages
  • All file formats
  • Custom limits
  • Unlimited concurrency
  • Dedicated support

FAQ

What is RunDocling?

RunDocling is an independent managed API service that runs Docling for you. We handle all the infrastructure—CPUs, GPUs, and scaling—so you can convert documents without managing heavy dependencies or hardware.

Are you affiliated with the Docling team?

No. We are not affiliated with IBM or the Docling open-source project. We simply provide a managed hosting service that makes it easier to use Docling via a REST API.

How does it work under the hood?

We run docling-serve, the official open-source API wrapper for Docling. This means all parameters and options are fully compatible with the Docling library. We just handle the infrastructure so you don't have to.

Is my data secure?

Yes. Your documents are processed in isolated environments and automatically deleted after 24 hours. We do not store, share, or use your documents for any purpose other than conversion. Be sure to save your results before they expire.

Why is it faster than running locally?

We run Docling on dedicated GPU infrastructure optimized for document processing. No cold starts, no resource contention—just fast, real-time conversion without you managing any hardware.

What file formats are supported?

We support PDF, DOCX, PPTX, XLSX, HTML, Markdown, images (PNG, JPG, TIFF), and more. Output formats include Markdown and JSON with preserved tables, layouts, and metadata.

Why did you build this?

We're developers who got frustrated. Every time we needed to parse a PDF for a quick test or process documents in a pipeline, it was a mess—dependencies, GPU setup, memory issues. We just wanted something that works in 10 seconds. So we built it.

Ready to get started?

Start converting documents in seconds. No credit card required.