1 credit per URL that comes back (0.5 when served from cache). URLs that fail, time out or hit a bot check are listed in failed and cost nothing.

How is this different from /v1/webpage?

/v1/webpage reads one URL. /v1/extract reads up to 20 in parallel, adds highlights and token caps, and reports per-URL failures instead of failing the whole call.

Are highlights generated by an LLM?

No. Passages are split along the page's headings and ranked against your query with BM25, a lexical ranker. It's deterministic and adds no cost.

Can it read pages behind a login?

No. Only public pages, the way a logged-out visitor sees them.

POST /v1/extract

Web Extract API

Up to 20 web pages or PDFs in, clean Markdown out, fetched in parallel. Add a question and get the passages that answer it instead of whole pages.

Get a free API key Read the reference

1 credit per URL that comes back (0.5 from cache); failed URLs are free 2,500 free credits, no card Failed calls are free

Overview

What the Web Extract API does

The Web Extract API reads many pages in one call: the same fetch and Markdown conversion as the Webpage API, PDFs included, for up to 20 URLs at once, fetched in parallel. Each page comes back with its final URL, status, title, published date and metadata, as markdown, text or raw html.

With query and highlights, each page also gets the passages most relevant to your question, ranked with BM25 (deterministic, no model involved). max_tokens caps each page instead, so a batch of pages fits a context window.

The response is 200 even when some URLs fail: each failure is listed in failed with a reason code and costs nothing.

Need data, not text? output_schema fills your JSON Schema from each page (+4 credits per page) and summary: true adds a short summary (+4), both written by Claude. See the AI Data Extraction API.

What you get

request object: urls (deduplicated), format, query.
results[] array: One entry per page read: url (final, after redirects), status_code, title, published_at, metadata, cached, markdown / text / html, and links, images, highlights (text, score, heading) when asked for.
results[].summary / summary_error string | null: With summary: true: the summary, or null and the reason it failed (not charged).
results[].output / output_error any: With output_schema: the JSON value matching your schema, or null and the reason it failed (not charged).
failed[] array: URLs that could not be read: url, error (code, message). Not charged.
meta object: request_id, credits_used, latency_ms, succeeded, failed, and llm (provider, model, tokens) when an AI step ran.

Request

POST /v1/extract

cURL

Python

TypeScript

fetch

PHP

curl https://api.serpkite.com/v1/extract \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"urls":["https://en.wikipedia.org/wiki/Web_crawler","https://www.rfc-editor.org/rfc/rfc9309.html"],"query":"robots.txt crawl delay","highlights":3}'

Response (illustrative, placeholder domains)

200 OK · application/json

{
  "request": {
    "endpoint": "extract",
    "urls": [
      "https://en.wikipedia.org/wiki/Web_crawler",
      "https://www.rfc-editor.org/rfc/rfc9309.html"
    ],
    "format": "markdown",
    "query": "robots.txt crawl delay"
  },
  "results": [
    {
      "url": "https://www.rfc-editor.org/rfc/rfc9309.html",
      "status_code": 200,
      "title": "RFC 9309: Robots Exclusion Protocol",
      "metadata": {
        "title": "RFC 9309: Robots Exclusion Protocol",
        "content_type": "text/html"
      },
      "cached": false,
      "markdown": "# Robots Exclusion Protocol\n\n…",
      "highlights": [
        {
          "text": "Crawlers SHOULD NOT use the cached version for more than 24 hours, unless the robots.txt is unreachable…",
          "score": 6.214,
          "heading": "Robots Exclusion Protocol > Caching"
        }
      ]
    }
  ],
  "failed": [
    {
      "url": "https://en.wikipedia.org/wiki/Web_crawler",
      "error": {
        "code": "upstream_timeout",
        "message": "the page did not load in time"
      }
    }
  ],
  "meta": {
    "request_id": "req_01J8ZK4M6Q2V7",
    "credits_used": 1,
    "latency_ms": 2210,
    "succeeded": 1,
    "failed": 1
  }
}

Every response also carries X-Credits-Used, X-Credits-Remaining, X-Cache and X-Tokens-Estimate headers. Full endpoint reference

Reference

Parameters

The fields /v1/extract accepts in its JSON body.

Web Extract API parameters
Name	Type	Default	Description
`urls` required	string[]	–	1–20 public http(s) URLs of HTML pages or PDFs.
`format`	string	markdown	What each result carries: markdown, text or the raw html. Values: markdown, text, html.
`query`	string	–	What highlights are ranked against (up to 4,096 characters).
`highlights`	integer	0	Passages per page ranked against query, 0–10 (about 600 characters each).
`max_tokens`	integer	–	Trim each page's Markdown or text to about this many tokens (100–100,000).
`include_links`	boolean	false	Webpage: also return the page's outbound links (url, text).
`include_images`	boolean	false	Webpage: also return the page's image URLs.
`max_age`	integer	–	Accept a cached page up to this many seconds old, for 0.5 credit.
`country`	string	–	Fetch the pages as seen from this country (two-letter ISO code).
`timeout`	integer	–	Seconds to wait for the pages, 1–90 (default 50, or 75 with summary or output_schema). A page still loading is listed in failed (upstream_timeout) and not charged.
`summary`	boolean	false	Add a 3–6 sentence AI summary of each page, focused on query when set. +4 credits per page; a failed summary is free.
`output_schema`	object	–	A JSON Schema (at most 16 KB). Each page's data comes back as JSON matching it in output. +4 credits per page; a failed extraction is free.
`prompt`	string	–	Guides the output_schema extraction: what to pick and how to normalise it (up to 4,096 characters). Needs output_schema.

Full reference, error codes and headers are in the /v1/extract reference.

Use cases

What people build with the Web Extract API

RAG over chosen sources

Read the URLs your retriever picked, as Markdown, in one round trip.

Answer-focused context

highlights returns only the passages that match the question, keeping prompts small.

PDF reading

Papers, filings and manuals in PDF come back as text alongside HTML pages.

Pricing

Web Extract API pricing

Cost per call

1 credit

per URL that comes back (0.5 from cache); failed URLs are free

From $0.60 per 1,000 URLs at volume.
Credits never expire. No subscription.
Failed, empty and blocked calls are refunded.
2,500 free credits = 2,500 URLs, then 1,000 credits a month.

See all pricing

Web Extract API cost per pack
Pack	Price	Per 1k credits	Per 1k URLs	URLs per pack
Starter	$10	$1.00	$1.00	10,000
Growth	$50	$0.80	$0.80	62,500
Pro	$300	$0.60	$0.60	500,000

FAQ

Web Extract API: common questions

Keep exploring

Related APIs and integrations

AI Data Extraction API Up to 20 URLs per call to JSON that matches your schema. Webpage to Markdown API Any URL to clean Markdown plus metadata, for RAG. Website Crawler API Crawl a site or section to Markdown, async, robots.txt respected. Website Map API A site's URLs from robots.txt, sitemaps and links, ranked by search.

Use it from

Start building

Start with the Web Extract API

2,500 free credits, then 1,000 every month. No credit card.