Zenserp compatible

The call, before and after

# Before
curl "https://app.zenserp.com/api/v2/search?q=Larkspur+Colorado+mayor" -H "apikey: $ZENSERP_API_KEY"

# After
curl "https://api.specstream.ai/zenserp/api/v2/search?q=Larkspur+Colorado+mayor" -H "apikey: $SPECSTREAM_API_KEY"

With Zenserp's Python client, zenserp 0.2, the change is one line, and the client sends the key in the apikey header as before:

zenserp.api_base = "https://api.specstream.ai/zenserp/api/v2"

What the route reads, and what it refuses

Read and applied: q, num (1 to 100), start, timeframe (h, d, w, m, y), tbs with a cdr: date range, ai_overview, and search_engine google.com.

Refused with 400 in Zenserp's form: tbm (news and the other tabs) and a search_engine that is not Google. A call with no key gets 403. Every parameter was measured on production on Nov 10, 2026 with zenserp 0.2, and the full pass table lists each one and its result.

Every field that comes back

The reply has query with the q you sent, organic[], number_of_results, and pagination with current_page, next_page, previous_page (null on the first page) and pages. Each result has position, title, url, destination and description. With ai_overview=1 the reply adds ai_overview with present, text, text_paragraphs and citations.

The route does not return query.url, related_searches, or a result's isAmp, extra, questions and images. One field is added, specstream, with the call's price_usd.

$5 per 1,000 searches, AI Overview included

On Zenserp an AI Overview request uses 3 searches of a monthly plan. On SpecStream every call of up to 10 results costs $0.005, with or without ai_overview, each started block of 10 more adds $0.006, and credit you buy never expires. 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 8,800 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. The full comparison is on the Zenserp alternative page.

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 answers the Zenserp call your code already sends.

SearchApi.io

Google results on monthly plans from $40 for 10,000 searches, with 100 free requests, in its own request and reply. SpecStream keeps Zenserp's request and reply, and scores 97.9 F-score on SimpleQA Verified.

Serper

Google results in credit packs from $1.00 per 1,000 for 50,000 credits, with 2,500 free queries and no card. SpecStream needs no new code, and its credit never expires.