You.com Search API compatible

The call, before and after

# Before
curl -X POST https://ydc-index.io/v1/search \
  -H "X-API-Key: $YDC_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?", "count": 5}'

# After
curl -X POST https://api.specstream.ai/you/v1/search \
  -H "X-API-Key: $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?", "count": 5}'

The youdotcom Python SDK takes the address on each search call, with the client built on a SpecStream key:

# Before
you.search(query=QUERY)  # You(api_key_auth=YDC_API_KEY)

# After
you.search(query=QUERY, server_url="https://api.specstream.ai/you")  # You(api_key_auth=SPECSTREAM_API_KEY)

Code on the older form, GET https://api.ydc-index.io/search with query and num_web_results, moves to https://api.specstream.ai/you/search and gets hits[] back. Every parameter and field on this page is in the pass table, measured on production on November 10, 2026.

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.

LiteLLM 1.108.4: set YOUCOM_API_BASE to https://api.specstream.ai/you and put your SpecStream key in YOUCOM_API_KEY. The call stays litellm.search(search_provider="you_com").

Every parameter the route uses

Used in the search: query, count (1 to 100), offset (0 to 9, in pages of count), freshness (day, week, month, year or a range written YYYY-MM-DDtoYYYY-MM-DD), include_domains and exclude_domains, as a JSON list or names apart by commas in the address.

Used to shape the reply: extraction with extraction_mode highlights adds contents.highlights to each result whose page answers the query. On the older form, query and num_web_results (1 to 19).

Refused with You.com's 422 {"error"}: a count over 100, a freshness You.com does not take, and include_domains sent with exclude_domains or boost_domains. A call with no key gets 401 {"detail"}.

Every field that comes back

The reply has results.web and metadata with search_uuid, query and latency in seconds. Each web result has url, title, description and snippets, page_age when the page has a date, and contents.highlights when you ask for highlights and the page answers.

Not returned: thumbnail_url, favicon_url, results.news and results.knowledge. The older form returns hits[] with url, title, description and snippets, and latency.

One field is added: specstream, with what the Search API returns beyond You.com's fields, including the call's price_usd. A parser that reads You.com's fields never sees it.

$5 per 1,000 searches, highlights included

A call of up to 10 results costs $0.005, with or without highlights. Each started block of 10 more results adds $0.006: count 20 costs $0.011 and count 100 costs $0.059. A call stopped by a 429 charges nothing, and credit you buy never expires.

The most accurate web search API, in about one second

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.

A call without highlights runs the fast search. Measured on production on November 9, 2026, its median was 0.82 s at 1 search a second and 1.07 s at 20 a second, the 95th percentile stayed between 1.09 and 1.73 s, and it answered 718 of 720. It takes up to 8,800 searches a minute on one account. A call with highlights, the SDK's default, runs the default search, which reads the pages, at the same price.

You decide what is kept, on each key

Create the 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, its answer is not reused for another call, and its log lines carry neither. 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 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 most a run can cost is approved before it starts. The full comparison is on the You.com alternative page.

Tavily

A search API sold in credits at $0.008 each pay as you go: a basic search takes 1 credit and an advanced search 2. SpecStream answers Tavily's POST /search at https://api.specstream.ai/tavily for $0.005, basic or advanced.

Exa

A search API on Exa's own index, at $7 per 1,000 requests on auto and $4 on lite for up to 10 results, with its own request and reply. SpecStream answers Exa's call as well, at https://api.specstream.ai/exa, for $0.005 a search.

Brave Search API

A search API on Brave's own index at $5 per 1,000 requests, with $5 in free credits every month and 50 queries per second. SpecStream answers Brave's call at https://api.specstream.ai/res/v1/web/search at the same price per call and takes up to 8,800 searches a minute on one account.