Linkup vs You.com in 2026
One key answers both calls.
Linkup charges $0.005 a search at standard depth and $0.05 at deep. You.com charges $5.00 per 1,000 calls of up to 100 results. Both allow 10 searches a second, and each has its own request and JSON.
SpecStream answers both calls with one key. Change https://api.linkup.so/v1 to https://api.specstream.ai/linkup/v1 and https://ydc-index.io to https://api.specstream.ai/you. Your code keeps its body and its parser.
A search of up to 10 results costs $0.001 on either path, $1 per 1,000. SpecStream scores 97.9 F-score on all 1,000 SimpleQA Verified questions and 64.0 item F1 on all 200 WideSearch tasks (benchmarks).
New accounts get $10 of credit, no card. It covers 10,000 searches.
SpecStream, Linkup and You.com side by side
| SpecStream | Linkup | You.com | |
|---|---|---|---|
| The call your code sends | Both, on one key. POST https://api.specstream.ai/linkup/v1/search in Linkup's JSON with the key as the Bearer token, and POST https://api.specstream.ai/you/v1/search in You.com's JSON with the key in X-API-Key | POST https://api.linkup.so/v1/search with q, depth and outputType, and a Linkup key as a Bearer token | POST https://ydc-index.io/v1/search with query and count, and a You.com key in X-API-Key. GET /v1/search still works and gets no new features |
| Price of a search | $0.001 for up to 10 results on either path: Linkup's flash, fast and standard with searchResults, and You.com's /v1/search with highlights. $0.005 at Linkup's deep or with sourcedAnswer | $0.005 at flash, fast or standard with raw results and $0.006 with a sourced answer. deep costs $0.05, or $0.055 with an answer | $5.00 per 1,000 calls of up to 100 results. One request is one billable call, whatever it returns |
| More results in one call | Up to 100 on either path. Each started block of 10 more results adds $0.0012: 40 results cost $0.0046 and 100 cost $0.0118 | The price depends on depth and outputType, not on the number of results | Up to 100 results in the same call at the same price |
| The text of each page | In the same search at no extra cost: You.com highlights, and Linkup's standard and deep. The Extract API reads any page at $0.80 per 1,000 pages | Fetch costs $0.001 a call in standard mode, up to $0.011 with a schema | Full page extraction costs $1.00 per 1,000 pages fetched live |
| Volume | No limit per key and no daily limit. Production answered 718 of 720 searches at up to 20 a second on November 9, 2026 | 10 queries a second per organization on Search and Fetch | 10 requests a second on /v1/search by default |
| Calls that fail | A busy call answers 429 in that API's own error form with Retry-After, and charges nothing. A call that returns no results costs nothing | No charge on an error or an empty result. An empty balance answers 429 | One request is one billable call, whatever it returns |
| Free to start | $10 of credit, no card, which covers 10,000 searches. Credit you buy never expires | $20 of credit at sign up with a professional email address, and eligible accounts are topped back up to $20 each month | $10 of free credit, which covers 2,000 searches |
| Every match as structured rows | Deep Search: a request in plain words returns every match on the live web as rows that meet each condition you wrote, at 5¢, 15¢ or $1 a row, plus 5¢ for an email and 15¢ for a phone. The most a run can cost is quoted before it starts | Research costs $0.25 to $2.50 a request | The Research API starts at $12 per 1,000 calls at lite |
Why teams choosing between Linkup and You.com use SpecStream
Keep both calls and change two lines
Your Linkup call and your You.com 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"}'
# You.com: was https://ydc-index.io/v1/search
curl -X POST https://api.specstream.ai/you/v1/search \
-H "X-API-Key: $SPECSTREAM_KEY" -H "Content-Type: application/json" \
-d '{"query": "Who founded Mistral AI and when?", "count": 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 You.com 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 /you/v1/search, by GET or POST, query, count from 1 to 100, offset from 0 to 9, freshness, include_domains and exclude_domains work as on You.com, and both domain lists together get 422, as on You.com. The reply has results.web[] with url, title, description, snippets and page_age when the page has a date, and metadata. extraction with extraction_mode highlights adds contents.highlights at no extra cost. results.news and results.knowledge are not returned. In the youdotcom Python SDK, pass server_url="https://api.specstream.ai/you" to you.search.
$1 per 1,000 searches, page text included
Linkup prices a search by depth and output, from $0.005 to $0.055. You.com charges $0.005 a call for up to 100 results, and page text read live adds $1.00 per 1,000 pages. On SpecStream a search of up to 10 results is $0.001 on either path, highlights and page text included. Up to 40 results a call, SpecStream costs less than You.com: 40 results are $0.0046. 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
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, and a page with no text is not charged. It 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.
Other search APIs for AI agents
Tavily
Search in credits at $0.008 a credit pay as you go, 1 credit for a basic search and 2 for an advanced one, with 1,000 free credits every month. SpecStream answers Tavily's POST /search at https://api.specstream.ai/tavily, in Tavily's JSON, at $0.001 a search.
Parallel
Search at $1 per 1,000 requests in turbo and fast and $5 in basic and advanced, with 600 requests a minute. SpecStream answers Parallel's POST /v1/search at https://api.specstream.ai/parallel, in Parallel's JSON, with no limit per key.
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 $0.001 a search.
Brave Search API
Results from Brave's own index at $5 per 1,000 requests, with $5 in free credits every month. SpecStream answers Brave's GET /res/v1/web/search at https://api.specstream.ai, at $1 per 1,000 searches.
How SpecStream scores
The same numbers as the benchmarks page, from the official tasks and scorers.
How to run your Linkup and You.com calls on SpecStream
1. Create a key under Agents & API in the workspace. A new account gets $10 of credit, no card, which covers 10,000 searches.
2. Point each client at its SpecStream path. Linkup's call sends the key as the Bearer token, and You.com's call sends it in X-API-Key. In Python:
import requests
KEY = SPECSTREAM_KEY
QUESTION = "Who founded Mistral AI and when?"
# Linkup's call, was https://api.linkup.so/v1/search
linkup = requests.post(
"https://api.specstream.ai/linkup/v1/search",
headers={"Authorization": f"Bearer {KEY}"},
json={"q": QUESTION, "depth": "fast", "outputType": "searchResults", "maxResults": 10},
timeout=60,
).json()
for result in linkup["results"]:
print(result["name"], result["url"])
# You.com's call, was https://ydc-index.io/v1/search
you = requests.post(
"https://api.specstream.ai/you/v1/search",
headers={"X-API-Key": KEY},
json={"query": QUESTION, "count": 10},
timeout=30,
).json()
for result in you["results"]["web"]:
print(result["title"], result["url"])3. In JavaScript:
const key = process.env.SPECSTREAM_KEY;
const question = "Who founded Mistral AI and when?";
// Linkup's call, was https://api.linkup.so/v1/search
const linkup = await fetch("https://api.specstream.ai/linkup/v1/search", {
method: "POST",
headers: { Authorization: `Bearer ${key}`, "Content-Type": "application/json" },
body: JSON.stringify({ q: question, depth: "fast", outputType: "searchResults" }),
}).then((r) => r.json());
// You.com's call, was https://ydc-index.io/v1/search
const you = await fetch("https://api.specstream.ai/you/v1/search", {
method: "POST",
headers: { "X-API-Key": key, "Content-Type": "application/json" },
body: JSON.stringify({ query: question, count: 10 }),
}).then((r) => r.json());
for (const result of linkup.results) console.log(result.name, result.url);
for (const result of you.results.web) console.log(result.title, result.url);4. Leave the rest. Each call is billed as one search from $0.001 for up to 10 results, and the reply's specstream.price_usd says what it cost. On a 429 with Retry-After, wait those seconds and send the call again; nothing was charged.
When your agent needs every match in place of a results page, write the request in plain words. SpecStream reads it back as the conditions every row must meet and the facts to bring back, quotes the most it can cost, and delivers the rows after you approve.
Companies that name Linkup as a subprocessor on their own published list, each with the page and the day we read it.
Frequently asked questions
Something we didn't answer? Talk to a human
Is Linkup better than You.com?
Linkup vs You.com pricing: what does each cost?
standard depth with raw results and $0.05 at deep. You.com costs $5.00 per 1,000 calls of up to 100 results, plus $1.00 per 1,000 pages of full page text read live. SpecStream costs $0.001 a search of up to 10 results on either path, page text included.Which one has a free plan?
Can I use both Linkup and You.com?
https://api.specstream.ai/linkup/v1 and You.com's at https://api.specstream.ai/you, each in its own JSON. One balance, one request log and one spending limit cover both.Do the Linkup and You.com SDKs work with SpecStream?
linkup-sdk takes base_url="https://api.specstream.ai/linkup/v1", and the youdotcom Python SDK takes server_url="https://api.specstream.ai/you" on each search call, with the SpecStream key in place of theirs. The calls and the replies stay as they are.How many searches a second can I run?
/v1/search by default.Sources
SpecStream wrote this page. Each figure for Linkup, You.com and the other APIs comes from that company's own page.
- Linkup pricingdocs.linkup.so/pages/documentation/platform/pricing, read Nov 12, 2026
- Linkup authenticationdocs.linkup.so/pages/documentation/platform/authentication.md, read Nov 12, 2026
- Linkup rate limitsdocs.linkup.so/pages/documentation/platform/rate-limits.md, read Nov 12, 2026
- Linkup Researchdocs.linkup.so/pages/documentation/endpoints/research/overview, read Nov 12, 2026
- Linkup introductiondocs.linkup.so/pages/documentation/get-started/introduction, read Nov 12, 2026
- Linkup billingdocs.linkup.so/pages/documentation/platform/pricing.md, read Nov 12, 2026
- You.com billingyou.com/docs/administration/billing.md, read Nov 12, 2026
- You.com plansyou.com/plans?hsLang=en, read Nov 12, 2026
- You.com rate limitsyou.com/docs/rate-limits.md, read Nov 12, 2026
- You.com Search API referencedocs.you.com/api-reference/search/v1-search.md, read Nov 12, 2026
- You.com Search API schemayou.com/docs/openapi/web-search.json, read Nov 12, 2026
- Tavily API creditsdocs.tavily.com/documentation/api-credits.md, read Nov 12, 2026
- Parallel search modesdocs.parallel.ai/search/modes.md, read Nov 12, 2026
- Parallel rate limitsdocs.parallel.ai/getting-started/rate-limits.md, read Nov 12, 2026
- Exa pricingexa.ai/docs/admin/pricing.md, read Nov 12, 2026
- Brave Search APIbrave.com/search/api/, read Nov 12, 2026
- SpecStream pricingspecstream.ai/pricing, read Nov 12, 2026
- SpecStream for agentsspecstream.ai/agents.md, read Nov 12, 2026
- SpecStream benchmarksspecstream.ai/benchmarks, read Nov 12, 2026




