Liner Search API compatible

The call, before and after

# Before
curl -X POST https://platform.liner.com/api/v1/tools/search/web \
  -H "x-api-key: $LINER_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "recent AI regulation updates", "date_range": "past_week", "max_results": 10}'

# After
curl -X POST https://api.specstream.ai/liner/api/v1/tools/search/web \
  -H "x-api-key: $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "recent AI regulation updates", "date_range": "past_week", "max_results": 10}'

The body and the parser stay. The base address changes to https://api.specstream.ai/liner, and the key changes. Every parameter and field below is what the route answers on November 13, 2026.

The $2 default, and what the same call costs here

Liner's docs say that since November 11, 2026, Premium Data is on by default, also for requests that do not send the option, and that those requests are billed at $2 per 1,000. A request with no matching data is still billed at $2 per 1,000. The camelCase includeKnowledge: false is ignored and billed at $2 per 1,000 as well.

On SpecStream a call of up to 10 results costs $0.001 whatever it sends for include_knowledge. Code written before November 11 keeps its $1 per 1,000 without an edit to the body.

Every parameter the route uses

Used in the search: query (required), max_results (1 to 20, 10 when you send none), date_range (past_day, past_week, past_month or past_year), country_code and lang.

include_knowledge is read and the reply holds web results. A date_range outside the four values or a max_results above 20 answers 400 with INVALID_REQUEST.

Every field that comes back

The reply has requestId, results and totalCount. Each result has title, url, hostname, faviconUrl, description and date, as YYYY-MM-DD when the page states one and null when it states none.

The reply has no knowledge key, the same reply Liner gives when no data matches the query, so a parser that checks for the key before reading it needs no change.

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

The Scholar search

The route answers the web search. A call to /api/v1/tools/search/scholar answers 400 with INVALID_REQUEST in Liner's error form and is never charged. Send a query for papers to /api/v1/tools/search/web: the reply has the same results[] without citationCount, authors and journal.

Errors in Liner's form, with retryable

Every refusal answers error with Liner's code, a message and retryable, so retry code that reads retryable works as it is. A missing or wrong key is UNAUTHORIZED with 401. A bad field is INVALID_REQUEST with 400. An empty balance is INSUFFICIENT_CREDITS with 402. A busy minute is RATE_LIMITED with 429, retryable set to true and a Retry-After header. None of them is charged.

$1 per 1,000 searches, and more credit on a large top-up

A search of up to 10 results costs $0.001. max_results from 11 to 20 costs $0.0022. A call stopped by a 429 charges nothing, and every charged reply carries the balance left in the X-Balance-Cents header.

Liner adds a 5% platform fee to credit purchases: its pricing page gives the example of $20 of credits costing $21. On SpecStream a top-up of $1,000 or more adds 20% more credit on the same payment: $1,000 buys $1,200 of searches.

In an MCP client

An agent that reached Liner through MCP connects to SpecStream's server at https://api.specstream.ai/mcp over Streamable HTTP, with OAuth or an API key. It then searches, reads pages and runs Deep Search from the same balance. Setup for each client is in the MCP docs.

The most accurate web search API

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.

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.

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 $0.001 a search.

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 $0.001 a basic search.

Brave Search API

A search API on Brave's own index at $5 per 1,000 requests and 50 queries per second. SpecStream answers Brave's call at https://api.specstream.ai/res/v1/web/search at $1 per 1,000, a fifth of Brave's rate.