Unnamed service

No provider description has been published.

Resource: pagedistill.thumm.workers.dev/extract

Network: base · Asset: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 · Pay to: 0x04f8B46edAD2C7c7d39067A4ADF3905f9b9B0B9B

Payment methods: — · Last validation: 2026-09-14 11:58:01.435+00

{
  "input": null,
  "output": null,
  "paymentRequirements": [
    {
      "raw": {
        "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
        "extra": {
          "name": "USD Coin",
          "version": "2"
        },
        "payTo": "0x04f8B46edAD2C7c7d39067A4ADF3905f9b9B0B9B",
        "scheme": "exact",
        "network": "base",
        "mimeType": "application/json",
        "resource": "https://pagedistill.thumm.workers.dev/extract?url=Required.+The+absolute+http%28s%29+URL+of+the+page+to+extract%2C+percent-encoded.",
        "description": "URL to clean JSON for AI agents. Fetches any public web page server-side and returns title, meta description, canonical URL, a heading outline, and boilerplate-stripped plain text — navigation, sidebars, cookie banners and footers removed. Saves an agent from running its own fetch + HTML-parsing + readability stack. Flat $0.01 per call, no account, no API key, no rate limit.",
        "outputSchema": {
          "input": {
            "type": "http",
            "method": "GET",
            "queryParams": {
              "url": "Required. The absolute http(s) URL of the page to extract, percent-encoded."
            },
            "discoverable": true
          },
          "output": {
            "type": "object",
            "required": [
              "url",
              "text",
              "word_count",
              "truncated",
              "content_root"
            ],
            "properties": {
              "url": {
                "type": "string",
                "description": "The URL that was fetched, after redirects."
              },
              "text": {
                "type": "string",
                "description": "Boilerplate-stripped plain text of the main content."
              },
              "title": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "Page title, or null if absent."
              },
              "headings": {
                "type": "object",
                "description": "Heading outline keyed h1..h6; each value is an array of heading strings."
              },
              "canonical": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "Canonical URL, or null."
              },
              "truncated": {
                "type": "boolean",
                "description": "True if `text` hit the length cap."
              },
              "word_count": {
                "type": "number",
                "description": "Word count of `text`."
              },
              "description": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "Meta/OG description, or null."
              },
              "content_root": {
                "type": "string",
                "description": "Which element the text was taken from: 'main', 'article' or 'body'."
              }
            }
          }
        },
        "maxAmountRequired": "10000",
        "maxTimeoutSeconds": 60
      },
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "payTo": "0x04f8B46edAD2C7c7d39067A4ADF3905f9b9B0B9B",
      "scheme": "exact",
      "network": "base",
      "amountAtomic": "10000"
    }
  ]
}

Source catalog records are retained separately from live endpoint observations. Sonar score, uptime, and latency are advisory metrics. CDP indexing is not inferred from validation.