Firecrawl crawl and map compatible

The call, before and after

# Before
curl https://api.firecrawl.dev/v2/crawl \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://quotes.toscrape.com/", "limit": 10}'

# After
curl https://api.specstream.ai/firecrawl/v2/crawl \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://quotes.toscrape.com/", "limit": 10}'

The reply is Firecrawl's: {"success": true, "id": "...", "url": "https://api.specstream.ai/firecrawl/v2/crawl/<id>"}. Read that url until status is completed, and follow next while it is set.

With firecrawl-py 4.55.0 the change is one line: Firecrawl(api_key=KEY, api_url="https://api.specstream.ai/firecrawl"). map, crawl with its waiter, start_crawl, get_crawl_status and cancel_crawl run as before. With @mendable/firecrawl-js 4.52.0 it is new Firecrawl({ apiKey: KEY, apiUrl: "https://api.specstream.ai/firecrawl" }), which passed 6 of 6 checks.

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.

LlamaIndex, llama-index-readers-web 0.7.0: pass api_url="https://api.specstream.ai/firecrawl" to FireCrawlWebReader, with your SpecStream key as api_key. Its crawl and map modes run through this route.

LangChain, langchain-firecrawl 0.1.0: pass api_url="https://api.specstream.ai/firecrawl" to FirecrawlLoader. Its crawl and map modes run through this route.

Dify: in the Firecrawl data source credential, set the base URL to https://api.specstream.ai/firecrawl. Its website crawl then runs on SpecStream.

What the route reads, and what it refuses

Map, applied: url, limit, search (matching links first), ignoreQueryParameters (on by default, as on Firecrawl), sitemap as include, skip or only, and includeSubdomains. A map gives up to 5,000 links.

Crawl, applied: url, limit, includePaths, excludePaths, maxDiscoveryDepth, crawlEntireDomain and scrapeOptions.formats with markdown, html, rawHtml and links. A crawl job reads up to 500 pages. start_crawl, the status read and DELETE to cancel work as Firecrawl's do.

Refused, in Firecrawl's own status and body: an unknown crawl id gets 404, a wrong key gets 401, a cancel of a finished job gets 409, and a call with no url gets 400. Every parameter was measured on production on Nov 10, 2026, and the full pass table lists each one and its result.

Every field that comes back

A map returns success and links[] with url. A crawl start returns success, id and url. A status read returns success, status, total, completed, creditsUsed, expiresAt, next and data[], each page with markdown, html, rawHtml and links as asked, and metadata with title, sourceURL, url, statusCode and error.

The route does not return links[].title and links[].description on a map, createdAt, completedAt and duration on a status read, or screenshot, metadata.description and metadata.language on a page.

One price a page, and a failed page is free

On Firecrawl a crawled page is 1 credit and a map is 1 credit, from a monthly plan: Hobby is $19 for 5,000 credits. On SpecStream every crawled page that gives text costs $0.0008, which is $0.80 per 1,000, and a map that gives links costs one page read, $0.0008. creditsUsed counts the pages charged. 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 Firecrawl's /v2/search and /v2/scrape at the same address, reads up to 20 pages or documents a call with the Extract API, and searches the web at $5 per 1,000 searches. 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 Firecrawl migration page.

Tavily map and crawl

Site maps and crawls billed in Tavily credits at $0.008 a credit on pay as you go. SpecStream answers Tavily's /map and /crawl at https://api.specstream.ai/tavily at $0.0008 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 at $0.80 per 1,000 pages.

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.

Exa

A search API with page contents at $1 per 1,000 pages. SpecStream reads pages at $0.80 per 1,000 and answers Exa's own call at https://api.specstream.ai/exa.