Firecrawl v1 compatible

The call, before and after

# Before
curl https://api.firecrawl.dev/v1/search \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "web scraping history", "limit": 5}'

# After
curl https://api.specstream.ai/firecrawl/v1/search \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "web scraping history", "limit": 5}'

The reply is v1's: success and data[], each result with url, title, description, and markdown when scrapeOptions.formats asks for it.

With firecrawl-py 4.55.0 the change is one line: V1FirecrawlApp(api_key=KEY, api_url="https://api.specstream.ai/firecrawl"). The client keeps the address's path and calls /firecrawl/v1/..., so scrape_url, search, map_url, async_crawl_url, check_crawl_status and cancel_crawl run as before.

What the route reads, and what it refuses

Scrape, applied: url and formats with markdown, html, rawHtml and links. A page the site answers 404 comes back with metadata.statusCode 404, as on Firecrawl.

Search, applied: query, limit, operators such as site:, tbs such as qdr:w, lang and country, and scrapeOptions.formats with markdown for the page text of each result.

Map, applied: url, limit, search, sitemapOnly, ignoreSitemap, includeSubdomains and ignoreQueryParameters (on by default). Crawl, applied: url, limit, maxDepth, maxDiscoveryDepth, includePaths and scrapeOptions.formats, up to 500 pages a job, with the status read and DELETE to cancel.

Refused, in Firecrawl's own status and body: an unknown crawl id gets 404 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.

Every field that comes back

A scrape returns data with markdown, html, rawHtml, links and metadata (title, sourceURL, statusCode, error). A search returns success and data[] with url, title, description, markdown and metadata. A map returns links as strings. A crawl status read returns success, status, total, completed, creditsUsed, expiresAt, next and data[].

The route does not return screenshot, metadata.description or metadata.language on a scrape.

One price a search, one price a page

On Firecrawl a search is 2 credits per 10 results and a page or a map 1 credit, from a monthly plan: Hobby is $19 for 5,000 credits. On SpecStream a search of up to 10 results costs $0.005, each started block of 10 more adds $0.006, a page costs $0.0008 and a page that gives no text costs nothing. A busy call gets 429 with Retry-After and charges nothing. Credit you buy never expires.

Speed, measured on production

On November 9, 2026 the fast search every drop-in route uses had a median of 0.82 s at 1 search a second and 1.07 s at 20 a second, and answered 718 of 720 calls. There is no limit per key and no daily limit.

Scored on the official benchmarks

The SpecStream 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. 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 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 address answers Firecrawl's v2 calls too, so a client can move to /v2 with no new key. The key 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 Firecrawl migration page.

Firecrawl v2

Firecrawl's newer API, on the same credits: Hobby is $19 a month for 5,000 credits. SpecStream answers v2's search, scrape, map and crawl at the same address, https://api.specstream.ai/firecrawl.

Tavily

Search and extract billed in credits at $0.008 a credit on pay as you go. SpecStream answers Tavily's call at https://api.specstream.ai/tavily at $0.005 a search.

Exa

A search API from $4 per 1,000 requests, with page contents at $1 per 1,000 pages. SpecStream answers Exa's own call at https://api.specstream.ai/exa and reads pages at $0.80 per 1,000.

Serper

Google results as JSON, in credit packs from $1.00 per 1,000 that are valid for 6 months. SpecStream answers Serper's call at https://api.specstream.ai/serper, reads the pages too, and its credit never expires.