read_page_backup
A second source for read_page: any web page as clean text or markdown, including pages built with JavaScript. ₹1.13 per page; a result that finds nothing is ₹0.
What it does
A second source for read_page, from a different data provider: any web page as clean text or markdown, including pages built with JavaScript. The answer is this provider's own, so its field names differ from read_page's: read the example answer, not read_page's docs.
Use it when read_page fails; read_page stays the first choice. It reads the same platform through another provider, so it helps when the first one is down or blocked, not when the platform has nothing. It is a separate call at its own price: you pay only when it finds something; a miss is free.
India: no locale knob; the page is fetched as its server serves it.
Inputs
Generated from the contract captured from staging on 2026-11-18.
| Field | Type | Required | Description |
|---|---|---|---|
url | string | yes | e.g. "https://example.com" |
mode | standard or pro | no | default "standard" |
renderJs | boolean | no | default false |
extractImages | boolean | no | default false |
What drives the cost
Flat price per call. A result that finds nothing is class: "ok_free", ₹0. The timeout is 30 seconds.
Price today
| Price today | ₹1.13 per page (cost_paise: 113) at ₹93.93 per US dollar on 17 November 2026 |
| Hold before the call | ₹1.70 (hold_paise: 170); when the call settles the real price is charged and the unused part is released |
| ₹0 when | it fails, or the provider answers but there is nothing in it (an empty list, no email, no page): class: "ok_free", ₹0 |
| Timeout | 30 s, then upstream_timeout (₹0, retryable) |
| Over MCP | run_tool with tool: "read_page_backup" |
| Over REST | POST https://api.parel.si/v1/run with "tool": "read_page_backup" |
| Confirmation | not needed (the estimate is under the ₹200 threshold) |
Request
curl https://api.parel.si/v1/run \
-H "Authorization: Bearer $PAREL_KEY" \
-H "Content-Type: application/json" \
-d '{"tool":"read_page_backup","input":{"url":"https://razorpay.com/about/"}}'
What comes back
data, as the live check of 2026-11-18 recorded it, trimmed:
{
"images": [],
"markdown": "Founded by IIT Roorkee alumni, Razorpay revolutionizes online payments by providing developer-friendly APIs and hassle-free integration.\n\n[Skip to content](#chakra-skip-nav)</>\n\nPaymentsOnline Payments\n\n[![](https://razorpay.com/build/brows…"
}
Notes
- Second source for read_page: call read_page first, this one after a failure.
- Field names differ from read_page's; inputs keep read_page's names where they mean the same thing.
Siblings
This page as Markdown: /docs/tools/read_page_backup.md. Something wrong or missing: hello@parel.si.