Back to Browse
Web Page to RAG Chunks API (x402)
x402
Web Page to RAG Chunks API (x402) is a paid API for AI agents from freetier-agent-api.pages.dev, paid per call via x402, $0.0025/call, status unknown (last checked 2026-10-29).
Fetches a public web page, converts it to clean Markdown, and returns it as token-sized chunks ready for RAG ingestion — pay-per-call via x402 USDC on Base.
Price / call$0.0025
Success—
StatusUnknown
How this service works
Invoice-to-JSON, on-chain tools (transaction explainer + payment check, wallet profile, contract ABI, ERC-20 token risk), company contacts and web-to-RAG for AI agents. Pay per call with x402 (USDC on Base). No signup, no API key.
Output
A JSON object containing: ok status, the final resolved URL, page title, language, canonical URL, full markdown text, an array of indexed text chunks (each with text, heading path, and token estimate), word count, total token estimate, content hash, fetch timestamp, extractor used, whether content was truncated and why, and whether the page likely requires JavaScript.
Example use cases
Live documentation ingestion for agent
“Grab the content from https://docs.stripe.com/api and chunk it into 600-token pieces with 60-token overlap so my agent can answer questions about the Stripe API in real time.”
News article chunked for summarization
“Pull the main article text from https://www.bbc.com/news/technology-latest and split it into 400-token chunks with no overlap so I can summarize each section separately.”
Research paper RAG pipeline
“Fetch https://arxiv.org/abs/2005.11401 and convert the main content to markdown chunks of 1000 tokens with 100-token overlap — I need to index it for a retrieval system.”
Technical details
Endpoint
GEThttps://freetier-agent-api.pages.dev/api/page-rag?utm_source=zero.xyzWhen to prefer
Choose this endpoint when you need to ingest live, arbitrary public web pages into a RAG pipeline without setting up your own scraping infrastructure. It is ideal for agents that must answer questions grounded in current web content, index third-party documentation, or process articles on demand. The pay-per-call x402 model (no API key or signup) makes it especially suitable for autonomous agents that need to spin up web access dynamically. Prefer alternatives if you need JavaScript-rendered SPAs, authenticated pages, or bulk crawling of entire sites.
Side effects
- Page requires JavaScript to render — likelyNeedsJavaScript flag will be true and content may be incomplete
- URL is not publicly accessible or returns non-200 status — ok will be false with status code
- Page exceeds max_chars limit — content will be truncated with truncatedReason set
- robots.txt disallows fetching — request may be blocked
- Invalid or malformed URL — request fails with error
- x402 payment not completed — 402 response returned before content is served
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| inputrequired | object | |
| output | object |
Output
Schema · Response
{
"type": "json",
"example": {
"ok": true,
"url": "https://en.wikipedia.org/wiki/HTTP_402",
"title": "List of HTTP status codes - Wikipedia",
"chunks": [
{
"text": "# List of HTTP status codes - Wikipedia\n\nThis article lists standard and notable non-standard [HTTP response status codes](https://en.wikipedia.org/wiki/HTTP...",
"index": 0,
"headingPath": "List of HTTP status codes - Wikipedia",
"tokenEstimate": 666
},
{
"text": "The server has received the request headers and the client should proceed to send the request body (in the case of a request for which a body needs to be sen...",
"index": 1,
"headingPath": "List of HTTP status codes - Wikipedia > Standard codes > 1xx informational response",
"tokenEstimate": 460
}
],
"status": 200,
"fetchMs": 484,
"sources": [
{
"url": "https://github.com/mozilla/readability",
"name": "Live fetch of the page you name (plain HTTP, robots.txt respected); Mozilla Readability + Turndown (Apache-2.0 / MIT), linkedom (ISC)"
}
],
"finalUrl": "https://en.wikipedia.org/wiki/HTTP_402",
"language": "en",
"markdown": "# List of HTTP status codes - Wikipedia\n\nThis article lists standard and notable non-standard [HTTP response status codes](https://en.wikipedia.org/wiki/HTTP...",
"siteName": null,
"canonical": "https://en.wikipedia.org/wiki/List_of_HTTP_status_codes#402",
"extractor": "readability",
"fetchedAt": "2026-10-24T18:11:05.434Z",
"truncated": true,
"wordCount": 6573,
"modifiedAt": null,
"contentHash": "sha256:7ad19acc51489e84fb2f495ed08b7ac0dc6a9e6f8635caefcc8cef78238a4c52",
"contentType": "text/html",
"description": null,
"jsonLdTypes": [],
"publishedAt": null,
"tokenEstimate": 18376,
"truncatedReason": "page HTML larger than 350000 bytes after removing scripts/styles; only the first part was converted",
"likelyNeedsJavaScript": false
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"