Capability · Framework — rag
Jina Reader
Jina Reader is the simplest URL-to-Markdown service for LLM workflows. You call r.jina.ai/<url> and get back rendered, de-cluttered Markdown with images and links preserved. The Reader engine is also open source, so you can self-host for private networks or strict data residency.
Framework facts
- Category
- rag
- Language
- TypeScript / Go
- License
- Apache-2.0
- Repository
- https://github.com/jina-ai/reader
Install
# No install — just call the API
curl https://r.jina.ai/https://engineering.vips.eduQuickstart
import requests
url = 'https://engineering.vips.edu/about'
markdown = requests.get(f'https://r.jina.ai/{url}').text
print(markdown[:500])Alternatives
- Firecrawl — multi-page crawler
- Trafilatura — local extraction with no API
- Mercury Parser — legacy reader mode
- Crawl4AI — async open-source crawler
Frequently asked questions
When to pick Jina Reader over Firecrawl?
Reader is ideal when you already have a list of URLs and want zero-setup Markdown. Firecrawl is better when you need to crawl a whole site with sitemap following and structured extraction.
Does Reader run JavaScript?
Yes, the hosted service renders JS. The self-host image also supports headless Chromium rendering.
Sources
- Jina Reader — GitHub — accessed 2026-04-20
- Jina Reader — landing — accessed 2026-04-20