Extract clean text
from any URL

Like Reader Mode, as an API. Strip ads, nav, footers, and clutter. Get pure content in one call. Built for AI pipelines, RAG, and content tools.

GET /extract
// Request
GET /extract?url=https://paulgraham.com/persistence.html

// Response
{
  "success": true,
  "data": {
    "title": "The Right Kind of Stubborn",
    "content": "Successful people tend to be persistent...",
    "author": "Paul Graham",
    "word_count": 1936,
    "reading_time_minutes": 8,
    "language": "en"
  }
}

Why ClearText

One endpoint

Send a URL, get clean text back. No complex setup, no SDK required. Just a GET request.

JS rendering

Toggle ?js=true for JavaScript-heavy sites. Works with SPAs, React, Next.js, and more.

Smart extraction

Powered by Mozilla's Readability algorithm. Strips ads, navigation, footers — keeps the content.

24h caching

Results are cached for 24 hours. Repeated requests are instant and don't count against your quota.

Built for AI

Clean text output ready for LLM ingestion, RAG pipelines, embeddings, and content analysis.

Fast & reliable

Average response in under 2 seconds. 99.9% uptime. Scales automatically with demand.

Simple pricing

Free

$0/mo
  • 100 requests / day
  • 10 requests / minute
  • 24h cache included
  • Standard extraction
Get started