Linkup compatible

The call, before and after

# Before
curl -X POST https://api.linkup.so/v1/search \
  -H "Authorization: Bearer $LINKUP_API_KEY" -H "Content-Type: application/json" \
  -d '{"q": "Who founded Mistral AI and when?", "depth": "fast", "outputType": "searchResults"}'

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

In the linkup-sdk Python client the change is the client line:

# Before
client = LinkupClient(api_key=LINKUP_API_KEY)

# After
client = LinkupClient(api_key=SPECSTREAM_API_KEY, base_url="https://api.specstream.ai/linkup/v1")

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.

Open WebUI: choose the web search engine linkup and put the address in its JSON setting LINKUP_SEARCH_PARAMS: {"url": "https://api.specstream.ai/linkup/v1/search"}.

LiteLLM 1.108.4: set LINKUP_API_BASE to https://api.specstream.ai/linkup/v1 and put your SpecStream key in LINKUP_API_KEY. The call stays litellm.search(search_provider="linkup").

Every parameter the route uses

Used in the search: q, depth (flash, fast, standard or deep, required as on Linkup), maxResults (1 to 100), includeDomains, excludeDomains, fromDate and toDate. The same fields work as a GET with the query string.

Used to shape the reply: outputType searchResults returns results[], and sourcedAnswer returns answer with its sources[].

Refused with Linkup's 400 body: outputType structured, a call with no depth or no outputType, and a fromDate after the toDate. A call with no key gets 401.

Every field that comes back

With searchResults, each result has type text, name, url, content and favicon, which is an empty string. With sourcedAnswer, the reply has answer and sources[], each with name, url, snippet and an empty favicon. The route returns no image results.

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

$5 per 1,000 searches, at every depth

A call of up to 10 results costs $0.005 at flash, fast, standard and deep, with searchResults or sourcedAnswer. On Linkup a deep search costs $0.05, and $0.055 with an answer. Each started block of 10 more results adds $0.006 on SpecStream: 20 results cost $0.011. A call stopped by a 429 for a busy search 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 searchResults call at flash or fast 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 at standard or deep, or with sourcedAnswer, 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 Linkup alternative page.

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.

Parallel

A Search API that starts at $1 per 1,000 requests, with 600 Search calls a minute on the Developer plan. SpecStream answers Parallel's own call at https://api.specstream.ai/parallel and takes up to 8,800 searches a minute on one account.