Kagi Search API compatible

The call, before and after

# Before
curl -X POST https://kagi.com/api/v1/search \
  -H "Authorization: Bearer $KAGI_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?"}'

# After
curl -X POST https://api.specstream.ai/kagi/api/v1/search \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?"}'

In Kagi's generated Python client the change is the host, and in kagiapi 0.2.1, on the v0 form, the base address:

openapi_client.Configuration(host="https://api.specstream.ai/kagi/api/v1", access_token=SPECSTREAM_API_KEY)
KagiClient.BASE_URL = "https://api.specstream.ai/kagi/api/v0"   # kagiapi, v0

Every parameter and field on this page is in the pass table, measured on production on November 10, 2026.

Apps and SDKs that take the address as a setting

Each line was run on production on November 10, 2026 through that client's own request and reply code. Put your SpecStream key wherever the client takes its key.

kagiapi 0.2.1, Kagi's v0 Python client: set KagiClient.BASE_URL = "https://api.specstream.ai/kagi/api/v0".

Every parameter the route uses

Used in the search: query, limit (up to 100 results returned), page (1 to 10), the lens fields sites_included, sites_excluded, keywords_included, keywords_excluded, file_type, time_after, time_before and time_relative (day, week, month), filters.after and filters.before, and personalizations.domains with kind block.

Used to shape the reply: extract.count (1 to 10) puts the page text of that many of the first results in their snippet. On the v0 form, q and limit.

Refused with Kagi's error body: a workflow other than search gets 400.

Every field that comes back

The reply has meta with trace and ms, and data.search. Each result has url, title, snippet, and time when the page has a date. Not returned: meta.node, image, props, related_search, direct_answer and infobox.

The v0 form returns meta.id and ms, and data[] with t, url, title, snippet and published. It does not return api_balance, thumbnail or related searches.

One field is added: specstream, with what the Search API returns beyond Kagi's fields, including the call's price_usd. A parser that reads Kagi's fields never sees it.

$5 per 1,000 searches, where Kagi charges $12

Kagi charges $12 per 1,000 search requests. On SpecStream a call of up to 10 results costs $0.005, with or without extract, and each started block of 10 more results adds $0.006: 20 results cost $0.011. A call stopped by a 429 charges nothing, and credit you buy never expires.

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 with no extract 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. It takes up to 8,800 searches a minute on one account. A call with extract runs the default search, which reads the pages, at the same price.

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: it is not in the history, its answer is not reused for another call, and its log lines carry neither. 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 Kagi Search API alternative page.

Brave Search API

A search API on Brave's own index at $5 per 1,000 requests, with $5 in free credits every month and 50 queries per second. SpecStream answers Brave's call at https://api.specstream.ai/res/v1/web/search at the same price per call and takes up to 8,800 searches a minute on one account.

Tavily

A search API sold in credits at $0.008 each pay as you go: a basic search takes 1 credit and an advanced search 2. SpecStream answers Tavily's POST /search at https://api.specstream.ai/tavily for $0.005, basic or advanced.

Exa

A search API on Exa's own index, at $7 per 1,000 requests on auto and $4 on lite for up to 10 results, with its own request and reply. SpecStream answers Exa's call as well, at https://api.specstream.ai/exa, for $0.005 a search.