ScraperAPI compatible

The call, before and after

# Before
curl -G https://api.scraperapi.com \
  --data-urlencode "api_key=$SCRAPERAPI_KEY" \
  --data-urlencode "url=https://en.wikipedia.org/wiki/Web_scraping"

# After
curl -G https://api.specstream.ai/scraperapi \
  --data-urlencode "api_key=$SPECSTREAM_API_KEY" \
  --data-urlencode "url=https://en.wikipedia.org/wiki/Web_scraping"

With ScraperAPI's Python SDK, scraperapi-sdk 1.6.1, the change is the constructor: client = ScraperAPIClient(SPECSTREAM_KEY, api_endpoint="https://api.specstream.ai/scraperapi"). client.get(url) then runs as before.

What the route reads, and what it refuses

Read and applied: url, api_key, and output_format with markdown or text. A page the site does not have comes back as ScraperAPI's 404.

Refused, in ScraperAPI's own status and text: no url gets 400, a wrong key gets 401, an empty balance gets 403, and a host that does not resolve gets 500 and is not charged. Every parameter was measured on production on Nov 10, 2026, and the full pass table lists each one and its result.

What comes back

A 200 reply is the page itself with its content-type: HTML by default, markdown or plain text with output_format. A refused call carries a sentence of text that says why, as ScraperAPI's does. No part of ScraperAPI's reply is left out.

One price a page, whatever the site

On ScraperAPI a Google or Bing page costs 25 credits and a LinkedIn page 30, and the balance resets each month. On SpecStream every page read costs $0.0008, which is $0.80 per 1,000, a failed page is not charged, and a busy call gets 429 with Retry-After and charges nothing. Credit you buy never expires.

Scored on the official benchmarks

The SpecStream Extract API scores 0.908 F1 on WCXB. The Search API scores 97.9 F-score on all 1,000 SimpleQA Verified questions, 978 of them correct, and 64.0 item F1 and 43.4 row F1 on all 200 WideSearch tasks. Every score and its method is on the benchmarks page.

You decide what is kept, on each key

Create the key with zero_retention and a call made with it keeps no request text and no answer after the reply. spend_cap_cents is the most the key can spend.

curl -X POST https://api.specstream.ai/v1/account/keys \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"name": "production", "scopes": ["account:read", "finds:spend"], "spend_cap_cents": 500000, "zero_retention": true}'

Pages, search and rows on one key

The same key reads up to 20 pages or documents a call with the Extract API, searches the web at $5 per 1,000 searches, and runs Deep Search, which returns every match for a request in plain words as structured rows, at 5¢, 15¢ or $1 a row, with a source URL on every value. The full comparison is on the ScraperAPI alternative page.

ScrapingBee

A page API from $19 a month for 75,000 credits, where a default call with JavaScript costs 5 credits and credits don't roll over. SpecStream answers ScrapingBee's call at https://api.specstream.ai/scrapingbee/api/v1/ too, at $0.80 per 1,000 pages.

ZenRows

A page API on monthly plans from $19 for 45,000 credits, where a JavaScript-rendered request always costs 5 credits. SpecStream charges one price a page and answers ZenRows' call at https://api.specstream.ai/zenrows/v1/.

Scrapfly

A page API from $30 a month for 200,000 credits, where browser rendering adds 5 credits a request. SpecStream answers Scrapfly's /scrape call too, and its credit never expires.

Firecrawl

Scrape, search and crawl in credits: Hobby is $19 a month for 5,000 credits. SpecStream answers Firecrawl's v2 calls at https://api.specstream.ai/firecrawl, and $19 reads 23,750 pages.