Linkup vs Tavily in 2026

Keep both calls and change two lines

Your Linkup call and your Tavily call keep their bodies, their headers and their parsers. Each one changes its address, and both carry the same key.

# Linkup: was https://api.linkup.so/v1/search
curl -X POST https://api.specstream.ai/linkup/v1/search \
  -H "Authorization: Bearer $SPECSTREAM_KEY" -H "Content-Type: application/json" \
  -d '{"q": "Who founded Mistral AI and when?", "depth": "fast", "outputType": "searchResults"}'

# Tavily: was https://api.tavily.com/search
curl -X POST https://api.specstream.ai/tavily/search \
  -H "Authorization: Bearer $SPECSTREAM_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?", "max_results": 10}'

A team that has not chosen yet writes to either format and moves nothing later. The parameter by parameter tables are in the Linkup migration guide and the Tavily migration guide.

What each path reads and returns

On /linkup/v1/search, by POST or GET, q, depth, maxResults from 1 to 100, includeDomains, excludeDomains, fromDate and toDate work as on Linkup. outputType takes searchResults, which returns results[] with type, name, url and content, and sourcedAnswer, which returns answer and sources[]. structured gets 400 with the reason. In linkup-sdk, set base_url to https://api.specstream.ai/linkup/v1.

On /tavily/search, query, search_depth, max_results from 0 to 20, include_answer and include_raw_content work as on Tavily. The reply has query, answer when asked, results[] with title, url, content, score, raw_content when asked and published_date when the page has a date, response_time and request_id. favicon and images are not returned. In the Tavily Python SDK, set api_base_url to https://api.specstream.ai/tavily.

$5 per 1,000 searches at every depth, from credit that does not expire

Linkup prices a search by depth and output, from $0.005 to $0.055. Tavily prices it in credits that reset each month, and an advanced search takes two. On SpecStream every search of up to 10 results is $0.005 on either path, deep, advanced, a sourced answer and page text included. There is no monthly plan, a top-up never expires, and a call stopped by a 429 charges nothing.

The most accurate web search API in the world

The SpecStream Search API scores a 97.9 F-score on all 1,000 official SimpleQA Verified questions, with 978 correct. Linkup reports a 94% F-score on the same benchmark. On WideSearch SpecStream scores 64.0 item F1 and 43.4 row F1 on all 200 official tasks, and the Extract API scores 0.908 F1 on WCXB. The scores and the method are at specstream.ai/benchmarks.

About one second a search, read live

Both paths run the fast search unless the call asks for page text or results past the first ten, and every search reads the live web at the moment of the call. On November 9, 2026 production took 1 to 20 fast searches a second 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. There is no limit per key and no daily limit.

Zero retention on any key

Set zero_retention when you create a key, or later. A search made with that key keeps no request text and no answer after the reply. The charge keeps the account, the key, the request ID, the price and the time.

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, crawls and rows on the same key

The same key reads up to 20 pages a call with the Extract API at $0.80 per 1,000 pages, answers Tavily's extract and map calls on the Tavily path, maps and crawls whole sites, and runs Deep Search, which returns every match on the live web as structured rows at 5¢, 15¢ or $1 a row. 10,000 rows with 5 facts each cost $500, and the most a run can cost is approved before it starts.

Exa

Search on its own index at $4 per 1,000 requests on lite and $7 on auto, for up to 10 results. SpecStream answers Exa's POST /search at https://api.specstream.ai/exa, in Exa's JSON, at $0.005 a search.

Parallel

Search from $1 per 1,000 requests, with 600 requests a minute on the Developer plan. SpecStream answers Parallel's POST /v1/search at https://api.specstream.ai/parallel, in Parallel's JSON, with no limit per key.

Brave Search API

Results from Brave's own index at $5 per 1,000 requests, with $5 in free credits every month and 50 queries a second. SpecStream answers Brave's GET /res/v1/web/search at https://api.specstream.ai, at $5 per 1,000 searches.

Serper

Google results as prepaid credits, from $1.00 per 1,000 on the 50k pack, and credits valid for 6 months. SpecStream answers Serper's POST /search at https://api.specstream.ai/serper, and a SpecStream top-up never expires.