LobeHub web search without hosting SearXNG

The .env before and after

LobeHub reads SEARXNG_URL from the server's environment and adds /search with format=json to it. SpecStream answers that call at https://api.specstream.ai/searxng/<key>, with the key as a part of the address, so LobeHub sends no header and needs none.

# .env before: a SearXNG container you host
SEARCH_PROVIDERS=searxng
SEARXNG_URL=http://searxng:8080

# .env after: no container
SEARCH_PROVIDERS=searxng
SEARXNG_URL=https://api.specstream.ai/searxng/YOUR_SPECSTREAM_KEY

SEARCH_PROVIDERS can stay unset, because searxng is LobeHub's default. Remove the SearXNG service from your docker-compose.yml once search answers.

This is the call LobeHub sends, and the one to try first from a shell:

curl "https://api.specstream.ai/searxng/$SPECSTREAM_API_KEY/search?q=latest+LobeHub+release&format=json"

Read pages on the same key

LobeHub reads the pages it cites with the crawlers named in CRAWLER_IMPLS. Set it to firecrawl and point FIRECRAWL_URL at SpecStream, with the version in the address. LobeHub adds /scrape and sends the key as a Bearer token.

# .env, added after the SearXNG lines
CRAWLER_IMPLS=firecrawl
FIRECRAWL_URL=https://api.specstream.ai/firecrawl/v2
FIRECRAWL_API_KEY=YOUR_SPECSTREAM_KEY

curl -X POST https://api.specstream.ai/firecrawl/v2/scrape \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://lobehub.com"}'

Already on Firecrawl? Change one URL

With SEARCH_PROVIDERS=firecrawl, LobeHub searches through FIRECRAWL_URL and adds /search. Set the address to https://api.specstream.ai/firecrawl/v2 and put the SpecStream key in FIRECRAWL_API_KEY: the search and the page reads both run on SpecStream, in Firecrawl's JSON. The Firecrawl migration guide lists every field.

# .env before
SEARCH_PROVIDERS=firecrawl
CRAWLER_IMPLS=firecrawl
FIRECRAWL_API_KEY=fc-...

# .env after
SEARCH_PROVIDERS=firecrawl
CRAWLER_IMPLS=firecrawl
FIRECRAWL_URL=https://api.specstream.ai/firecrawl/v2
FIRECRAWL_API_KEY=YOUR_SPECSTREAM_KEY

What stays the same

LobeHub's own SearXNG and Firecrawl code reads the reply, unchanged. The SearXNG route returns results[] with title, url and content, 10 results a search. The Firecrawl route returns data.web[] for a search and data.markdown for a page. Every parameter and field is in the SearXNG migration guide.

$0.005 a search and $0.0008 a page

A search of up to 10 results costs $0.005, which is $5 per 1,000, with no daily limit. Each page read through the Firecrawl scrape or Exa contents route costs $0.0008, which is $0.80 per 1,000 pages, and a page with no text costs nothing.

There is no monthly plan, no credit pack that expires and no reset on the first of the month. Credit you buy never expires.

The most accurate web search API in the world

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.

About one second a search, measured under load

Every drop-in route runs on the fast search. On November 9, 2026 production took 1, 5, 10 and 20 searches a second through it and answered 718 of 720. The median was 0.82 s at 1 search a second and 1.07 s at 20 a second, and the 95th percentile stayed between 1.09 and 1.73 s. One account can send up to 26,666 searches a minute; a call over that gets a 429 with Retry-After and is not charged.

You decide what is kept, on each key

Give LobeHub a 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 and its log lines carry neither. The charge keeps the account, the key, the request ID, the price and the time. 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 takes a request in plain words and returns every match on the live web as structured rows, at 5¢, 15¢ or $1 a row, with a source URL on every value.

SearXNG, self-hosted

LobeHub's default. It needs a working Docker or Podman installation, and an instance without the JSON format answers 403. An engine that answers too many requests is suspended for 3,600 seconds, and one that shows a CAPTCHA for 86,400. SpecStream answers the same call at $0.005 a search, with no server to run.

Firecrawl

Search at 2 credits per 10 results, on a free plan of 500 searches or 1,000 pages and paid plans from $19 a month for Hobby. Set FIRECRAWL_URL to https://api.specstream.ai/firecrawl/v2 and the same calls cost $0.005 a search and $0.0008 a page, on credit that never expires.

Tavily

Search and extract billed in credits at $0.008 each on pay as you go, with 1,000 free credits a month. LobeHub fixes Tavily's address at https://api.tavily.com. SpecStream searches the live web at $0.005 a search through SEARXNG_URL, with 97.9 F-score on all 1,000 SimpleQA Verified questions.

Exa

Search at $7 per 1,000 requests on auto and $4 on lite, and page contents at $1 per 1,000 pages per content type. LobeHub fixes Exa's address at https://api.exa.ai. SpecStream reads pages at $0.80 per 1,000 through FIRECRAWL_URL.

Brave

Search at $5 per 1,000 requests with $5 in free credits each month, and no page reader in LobeHub. SpecStream searches at the same $5 per 1,000 and reads the pages too, on one key.