URL to Text

Get the text of a web page quickly, without rendering JavaScript. Suits most content sites.

Pay by wallet (x402) url-to-text

Example

Input
{
  "url": "https://strale.dev"
}
Answer
{
  "url": "https://strale.dev",
  "text": "Strale — Trust and Quality Infrastructure for AI Agents",
  "title": "Strale — Trust and Quality Infrastructure for AI Agents",
  "language": "en",
  "meta_description": "Company data, compliance checks, financial validation. Structured JSON with audit trails on every call."
}

Inputs

FieldTypeRequiredWhat it is
urlstringYesURL to extract text from

Output fields

How reliably each field appears in a successful answer.

FieldTypeAppears
textstringAlways (present in every successful answer)
titlestringAlways (present in every successful answer)
languagestringAlways (present in every successful answer)
meta_descriptionstringAlways (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "url-to-text",
    "inputs": {
      "url": "https://strale.dev"
    },
    "max_price_cents": 2
  }'

Limitations

  • Text includes navigation and page boilerplate

    Extracts text from the rendered page — navigation, footers, and boilerplate content are included alongside main content

    What to do instead: Use url-to-markdown for cleaner output that better separates main content from page chrome

  • Pages are limited to 16 MiB of HTML

    Pages with more than 16 MiB of HTML are refused with a caller_input error naming the input field. The call is not charged, and the page is not retried through another fetch or rendering route.