Yandex Search API compatible

The call, before and after

# Before
curl -X POST "https://searchapi.api.cloud.yandex.net/v2/web/search" \
  -H "Authorization: Api-Key $YANDEX_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": {"searchType": "SEARCH_TYPE_COM", "queryText": "pizza"}, "folderId": "<folder>"}'

# After
curl -X POST "https://api.specstream.ai/yandex/v2/web/search" \
  -H "Authorization: Api-Key $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": {"searchType": "SEARCH_TYPE_COM", "queryText": "pizza"}, "folderId": "<folder>"}'

The reply is Yandex's: {"rawData": "PD94bWwg..."}. Decoded, it is the yandexsearch document your parser already reads: request with query, page, sortby and groupings, then response with reqid, found, found-human and results/grouping, one group per result.

Yandex's Python SDK, yandex-ai-studio-sdk, speaks gRPC and has no REST address setting, so the switch is in your own HTTP call: the address and the key. folderId can stay in the body.

What the route reads, and what it refuses

Applied: query.queryText, query.searchType as the search's country and language (SEARCH_TYPE_RU, TR, COM, KK, BE, UZ), query.page, query.familyMode, groupSpec.groupsOnPage from 1 to 100, period and the older resultsWithin, and sortSpec.sortMode with SORT_MODE_BY_TIME for dated results newest first. A call that names no count reads 10.

Refused, in Yandex Cloud's own {"code", "message", "details"} body: a queryText over 400 characters gets 400, as on Yandex, responseFormat FORMAT_HTML gets 400 with a message that names FORMAT_XML, 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.

The route answers the synchronous search. The deferred form, searchAsync and its operation, is not served.

Every field that comes back

In the XML: request with query, page, sortby, maxpassages and groupings/groupby, and response with its date, reqid, found, found-human and results/grouping with found, found-docs, found-docs-human and page. Each group has categ, doccount, relevance and a doc with url, domain, title and passages/passage. A search with no results carries Yandex's error code 15.

The route does not return misspell, reask, doc@id, headline, size, charset, properties, mime-type or saved-copy-url, and relevance is empty. modtime comes back when the source gave a date.

One price a search, on one key

On SpecStream a search of up to 10 results costs $0.005, which is $5 per 1,000, each started block of 10 more adds $0.006, and a busy call gets 429 with Retry-After and charges nothing. There is no folder or IAM token to set up, the same key reads the page behind any result at $0.0008, and 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.

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.

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.