---
title: "Deploy Docling Serve"
description: "API-key-protected CPU document conversion"
category: "AI/ML"
url: https://railway.com/deploy/docling-serve
---

# Deploy Docling Serve

API-key-protected CPU document conversion

**[Deploy Docling Serve on Railway](https://railway.com/template/docling-serve)**

- **Creator:** Tom
- **Category:** AI/ML

## Template content

### docling-serve https://raw.githubusercontent.com/monotykamary/railway-template-docling-serve/59f660564719eb592001d4bbdd85dbeffaff47f6/assets/docling-icon.png

- **Source:** https://github.com/monotykamary/railway-template-docling-serve
- **Health check:** /readyz
- **Public domain:** Yes

## Documentation

# Deploy and Host Docling Serve on Railway

## About Hosting Docling Serve

Docling Serve exposes Docling's document understanding and conversion pipelines through synchronous and asynchronous REST APIs and an optional web UI. This template deploys stable CPU-only version 1.30.0 with generated API-key protection and bounded production defaults.

Authenticate conversion requests with the `X-Api-Key` header set to the generated `DOCLING_SERVE_API_KEY` value.

## Common Use Cases

- Convert PDF, DOCX, PPTX, HTML, images, Markdown, and spreadsheets
- Extract structured Markdown, JSON, text, HTML, and DocTags
- Add document conversion to ingestion and retrieval pipelines

## Dependencies for Docling Serve Hosting

### Deployment Dependencies

- One CPU-only Docling Serve service
- Railway managed HTTPS
- Sufficient memory and CPU for selected document pipelines

### Implementation Details

The service is stateless. Readiness waits for model loading and the local orchestrator. Generated API-key auth protects conversion routes. Remote services, external plugins, custom remote model configs, and verbose error details are disabled. Requests are bounded to 20 MiB, 50 pages, and a 300-second synchronous wait.

Health and metrics endpoints remain public by upstream design. Submitted documents and temporary results are not durable.

## Why Deploy Docling Serve on Railway?

Railway provides managed HTTPS, generated API credentials, health-checked model startup, resource metrics, and Git-driven rollouts for document conversion workloads.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/docling-serve