Use case
An HTML to Markdown API backed by an index.
One authenticated GET turns any public URL into clean Markdown: navigation, cookie banners, and boilerplate stripped, headings and links kept. Because it serves from the Lyrenth index instead of converting from scratch per request, the same URL is instant for every caller after the first.
Get API access →Free tier · 2,000 reads/mo · no credit card
One line, clean Markdown
GET /v1/read?url=... with a Bearer key returns the page as Markdown. curl, Python, Node, or any HTTP client; nothing to install.
JS pages included
Pages that only exist after JavaScript runs are rendered by the index's headless fleet and serialized properly, including shadow-DOM web components.
60-99% fewer tokens
Measured on real pages, not promised: the benchmarks below are the API's own economics numbers for famous documentation pages.
Grows with your pipeline
The same read is available as a full AIDocument (structure, JSON-LD, signals, cache truth, economics) the day you need more than text.
Measured, not promised
Real pages, read through the production index, with the economics the API itself reports:
| Stripe API reference | 307,902 raw | 2,000 indexed | 99.4% saved |
| Vercel Functions docs | 237,390 raw | 2,149 indexed | 99.1% saved |
| Python asyncio docs | 6,175 raw | 1,251 indexed | 79.7% saved |
Free tier is 2,000 reads a month with no card: enough to point at your real URLs today and see the token difference in your own logs.
Get API access →First 1,000 builders: Starter free for 3 months