Scale SERP compatible

The call, before and after

# Before
curl "https://api.scaleserp.com/search?q=pizza&api_key=$OLD_API_KEY"

# After
curl "https://api.specstream.ai/scaleserp/search?q=pizza&api_key=$SPECSTREAM_API_KEY"

In Scale SERP's own Python example the change is the address and the key in one call: requests.get("https://api.specstream.ai/scaleserp/search", {"api_key": SPECSTREAM_KEY, "q": "pizza"}).

What the route reads, and what it refuses

Read and applied: q, num (1 to 100), page, time_period (last_hour, last_day, last_week, last_month, last_year, or custom with time_period_min and time_period_max as MM/DD/YYYY), tbs, gl, hl, lr, cr, safe, include_ai_overview, search_type=news with sort_by, and pagination.api_pagination.next for the next page.

Refused: search_type=images and the other result types get 400, and a call with no api_key gets 401, in Scale SERP's request_info form. Every parameter was measured on production on Nov 10, 2026, and the full pass table lists each one and its result.

Every field that comes back

The reply has request_info.success, search_metadata with created_at, processed_at and total_time_taken, search_parameters with q and engine, search_information with original_query_yields_zero_results, total_results, time_taken_displayed and query_displayed, pagination with current and api_pagination, and organic_results[] with position, title, link, domain, displayed_link, snippet and date. A news search returns news_results[] with position, title, link, domain, source, date, date_utc and snippet.

The route does not return request_info.credits_used or credits_remaining, the search_metadata links, search_tabs, knowledge_graph, related_searches, related_questions, top_stories, local_results or ads, nor a result's rich_snippet, sitelinks, about_this_result, prerender or thumbnail. One field is added, specstream, with the call's price_usd.

One price a search, AI Overview and news included

On Scale SERP an AI Overview takes 1 additional credit. On SpecStream every call of up to 10 results costs $0.005, a news search or an AI Overview included, each started block of 10 more adds $0.006, and there is no plan to renew. A busy call gets 429 with Retry-After and charges nothing.

The most accurate web search API, in about one second

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

A call of up to 10 results on the first page runs the fast search. Measured on production on November 9, 2026, its median was 0.82 s at 1 search a second and 1.07 s at 20 a second, the 95th percentile stayed between 1.09 and 1.73 s, and it answered 718 of 720. One account can send up to 26,666 searches a minute.

You decide what is kept, on each key

Create the key with zero_retention and a search 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}'

Search, pages and rows on one key

The same key reads up to 20 pages or documents a call with the Extract API at $0.80 per 1,000 pages, and a page with no text is not charged. Deep Search 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 most a run can cost is approved before it starts.

SerpWow

Traject Data's multi-engine API: Starter is $125 a month billed annually for 10,000 credits, then $.024 per extra credit. SpecStream answers SerpWow's own /live/search call at /serpwow, at $0.005 a search.

Scrapingdog

A scraping API whose Google search costs 5 credits a request: Lite is $40 a month for 200,000 credits, which is 40,000 searches at $1 per 1,000. SpecStream answers Scrapingdog's own /google call at /scrapingdog, with no plan.

SerpApi

Google results on monthly plans: Starter is $25 for 1,000 searches with 200 an hour, Developer $75 for 5,000. SpecStream charges $0.005 a search with no plan, and its credit never expires.