Tavily map compatible

The call, before and after

# Before
curl -X POST https://api.tavily.com/map \
  -H "Authorization: Bearer $TAVILY_API_KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://quotes.toscrape.com/", "select_paths": ["/author/.*"]}'

# After
curl -X POST https://api.specstream.ai/tavily/map \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://quotes.toscrape.com/", "select_paths": ["/author/.*"]}'

The reply is Tavily's: {"base_url": "https://quotes.toscrape.com/", "results": ["https://quotes.toscrape.com/author/Albert-Einstein", ...], "response_time": ..., "request_id": "..."}.

With tavily-python 0.8.5 the change is one line: TavilyClient(api_key=KEY, api_base_url="https://api.specstream.ai/tavily"). client.map(url) runs as before, and the same client's search and extract answer at that address too.

What the route reads, and what it refuses

Applied: url, also as a bare host such as quotes.toscrape.com, limit, max_depth (depth 1 is the start page's links, a deeper map adds the pages the site's sitemaps publish), and the regular expressions in select_paths, exclude_paths, select_domains and exclude_domains.

Refused, in Tavily's own status and body: a pattern that is not a valid regular expression gets 400 before the map is charged, max_depth past 5 gets 400, and a wrong key gets 401. Every parameter was measured on production on Nov 10, 2026, and the full pass table lists each one and its result.

Tavily's POST /crawl answers every page's content in one reply, and it is not served at /tavily/crawl. A crawl on SpecStream is a job you start and then read: Firecrawl's /v2/crawl on the same key, with includePaths, excludePaths, limit and maxDiscoveryDepth.

Every field that comes back

base_url, results as a list of URL strings, response_time in seconds and request_id. The route does not return usage; the price of a map is fixed at $0.0008.

One price a map

On Tavily a map costs 1 API credit per 10 pages, so a map of 500 URLs is 50 credits, $0.40 at $0.008 a credit. On SpecStream every map that gives links costs $0.0008, one page read, up to 5,000 URLs. A busy call gets 429 with Retry-After and charges nothing. Credit you buy never expires.

Scored on the official benchmarks

The SpecStream Extract API scores 0.908 F1 on WCXB. The 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. 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 answers Tavily's /search at $0.005 and /extract at $0.0008 a page, and reads up to 20 pages or documents a call with the Extract API. 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 full comparison is on the Tavily alternative page.

Firecrawl map and crawl

Map and crawl in credits: a map is 1 credit a call and Hobby is $19 a month for 5,000 credits. SpecStream answers Firecrawl's /v2/map and /v2/crawl at https://api.specstream.ai/firecrawl, $0.0008 a map or a page.

Spider

A scrape and crawl API billed by bandwidth, from $1 per GB, plus CPU time. SpecStream answers Spider's scrape and search at https://api.specstream.ai/spider, and a page costs $0.0008.

Crawl4AI

An open-source crawler you host and run yourself. SpecStream answers the Crawl4AI server's /crawl and /md at https://api.specstream.ai/crawl4ai, with no server to keep up.