Serply compatible

The call, before and after

# Before
curl -H "X-Api-Key: $SERPLY_API_KEY" \
  "https://api.serply.io/v1/search/?q=search+api&num=10"

# After
curl -H "X-Api-Key: $SPECSTREAM_API_KEY" \
  "https://api.specstream.ai/serply/v1/search/?q=search+api&num=10"

The reply is Serply's: {"results": [{"title": "...", "link": "https://...", "description": "...", "position": 1, "realPosition": 1, "result_type": "organic", "metadata": {"display_url": "..."}}, ...], "ads_count": 0, "ts": ..., "query": "q=search+api&num=10"}.

The serply package on PyPI writes https://api.serply.io/ into its client and sends the key as apikey with the query in the path, /v1/search/q=.... The route reads that header and that path form too.

What the route reads, and what it refuses

Applied: q in the query string or in the path, num up to 10 (a larger num gets 10, Serply's own ceiling), start as the offset, tbs such as qdr:w, and Google's gl, hl, lr, cr and safe. The X-Proxy-Location header sets the search's country.

Refused, in Serply's own {"detail": "..."} body: an empty q gets 400 and a call with no key gets 401. 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

results[] with title, description, link, position, realPosition, result_type, metadata.display_url and metadata.attributes, and at the top level ads_count, carousel_count, ts and query.

The route does not return ai_overview. ads, answers, image_results, shopping_ads, places, local_businesses, related_searches, carousel, company, total, knowledge_graph, related_questions, device_region and device_type come back empty, so a parser that reads them keeps working.

One price a search

On SpecStream a search of up to 10 results costs $0.005, which is $5 per 1,000, from a balance with no plan, and a busy call gets 429 with Retry-After and charges nothing. The same key reads the page behind any result at $0.0008, so a search and its pages are one bill. Credit you buy never expires.

Speed, measured on production

On November 9, 2026 the fast search every drop-in route uses had a median of 0.82 s at 1 search a second and 1.07 s at 20 a second, with the 95th percentile between 1.09 and 1.73 s, and answered 718 of 720 calls. There is no limit per key and no daily limit.

Scored on the official benchmarks

The SpecStream 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. The Extract API scores 0.908 F1 on WCXB. 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 at $0.80 per 1,000 pages. 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.

Serper

Google results as JSON, in credit packs from $1.00 per 1,000 that are valid for 6 months. SpecStream answers Serper's call at https://api.specstream.ai/serper, and its credit never expires.

SerpApi

Search engine result pages as JSON, sold by monthly plan: Starter is $25 a month for 1,000 searches. On SpecStream $25 pays for 5,000 searches, and SpecStream answers SerpApi's call too.

Brave Search API

A search API on Brave's own index at $5 per 1,000 requests. SpecStream answers Brave's call at https://api.specstream.ai/res/v1/web/search and reads the pages behind the results on the same key.