Keenable alternative

The whole migration is two values

Keenable's SDKs read the base address from base_url (or KEENABLE_API_URL). Point it at SpecStream and send a SpecStream key. The paths, the parameters and the reply stay Keenable's.

# Before
curl -X POST https://api.keenable.ai/v1/search \
  -H "X-API-Key: $KEENABLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Which US banks failed in 2026", "max_results": 10}'

# After
curl -X POST https://api.specstream.ai/keenable/v1/search \
  -H "X-API-Key: $SPECSTREAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Which US banks failed in 2026", "max_results": 10}'

$1 per 1,000 searches from the first call

Keenable's $1 rate needs dedicated capacity at 100 requests per second or more, which Keenable puts at about 8.6 million requests a day. Below that, a search or a fetch costs $4 per 1,000. SpecStream charges $1 per 1,000 searches of up to 10 results at any volume, and $0.80 per 1,000 pages read. A call that returns no results costs nothing.

The most accurate web search API in the world

On November 8, 2026 the SpecStream Search API scored 97.9 F-score on all 1,000 official SimpleQA Verified questions, 978 of them correct, and 64.0 item F1 and 43.4 row F1 on all 200 official WideSearch tasks. Every score and its method are on the benchmarks page.

Every page read at the moment of the call

An index answers from the copy it stored. SpecStream reads the live web for each call, and a fetch on the Keenable route reads the page as it is now, so live=true is the normal case and costs the same $0.80 per 1,000 pages.

The answer and its rows on the same key

On the same key, GET /v1/web-search does the reading for $5 per 1,000. The reply carries the answer with its page and its read time in seen_at, rows with the facts the request asks for, and sources, the results read in rank order. Add passages=true and it also holds the text of the top pages closest to the question.

From one search to a full dataset

When your product needs every match as a list, Deep Search returns it as structured rows, each value with its source URL and read time. A row costs 5¢, 15¢ or $1 by how much it needs, the most a run can cost is approved before it starts, and the rows reach your sheet, your CRM, Slack or your agent. Public records SpecStream already holds are at specstream.ai/data.

SpecStream

The live web data engine for teams and agents. It answers Keenable's own /v1/search and /v1/fetch at $1 per 1,000 searches of up to 10 results and $0.80 per 1,000 pages, and the same key returns answers with their pages and full datasets at 5¢, 15¢ or $1 a row. New accounts get $10 of credit, no card.

Brave Search API

A search API at $5 per 1,000 requests, with $5 in free credits every month. SpecStream answers Brave's own /res/v1/web/search call in Brave's JSON at $1 per 1,000: see the Brave Search API alternative.

Exa

A search API priced by the request: $4 per 1,000 on lite, $7 on auto and fast, and page contents at $1 per 1,000 pages for each content type. SpecStream answers Exa's own calls at https://api.specstream.ai/exa, with pages at $0.80 per 1,000: see the Exa alternative.

Tavily

A search API for agents billed in credits at $0.008 each pay as you go, with 1,000 free credits every month. SpecStream answers Tavily's own call at https://api.specstream.ai/tavily/search for $0.001 a search: see the Tavily alternative.

Parallel

A search API with modes: turbo at $1 per 1,000 requests and basic at $5, and a request with no mode runs advanced. SpecStream answers Parallel's own call at https://api.specstream.ai/parallel: see the Parallel alternative.