NewYour Exa or Tako SDK, up to 5× cheaper.

Compared with Linkup

vsLinkup

The Linkup alternative for news search

Linkup searches the whole web for AI and can write sourced answers. typesearch is built for the news: every result with its outlet, publication time and a calibrated relevance probability, the top ones read before they’re ranked — $1.40 per 1,000 searches, against $5 for a standard Linkup search.

Checked Sep 25, 2026 · A web search API for AI, with sourced answers

Mode by mode, per 1,000 searches

  • typesearch · Fast

    $1.40per 1,000

    Linkup: $5−72%

    Search, standard depth

  • typesearch · Normal

    $2.20per 1,000

    Linkup: $5−56%

    Search, standard depth

  • typesearch · Deep

    $5.60per 1,000

    Linkup: $50−88%

    Search, deep depth

Linkup bills per call: $5 per 1,000 standard searches with a list of results, $6 with an answer, and $50–55 per 1,000 deep searches. Errors aren’t charged. It doesn’t read or verify results; our normal and deep modes do.

Checked Sep 25, 2026 · Sources: docs.linkup.so/pages/documentation/platform/pricing

Side by side

What Linkup publishes, next to what typesearch does. Each of their facts links to where we read it.

Side by sideLinkuptypesearch
PricingPrepaid per call: $5 per 1,000 standard searches, $50 per 1,000 deep; answers cost $1–5 more Pay as you go, per search: $1.40 fast, $2.20 normal, $5.60 deep, per 1,000. No plan, no minimum
Free plan$20 with a professional email, topped back up to $20 a month for eligible accounts $5 in credit once, valid 30 days — not limited to development or testing
How far backThe web, with fromDate and toDate filters A rolling 30-day window: built for what’s happening now
CoverageThe web; no country or language parameters Sources in 130+ countries and 30+ languages; counts by country and language in GET /v1/sources
Full article textExtracted text per result; full pages with Fetch No: title, the outlet’s standfirst and short verbatim excerpts, always with the link
Per requestSet with maxResults Up to 50 judged results; up to five queries per request
RankingLinkup’s ranking; no publication date in results A calibrated relevance probability per result; the top ones read and verified in normal and deep
EnrichmentSourced answers and structured output with your JSON schema Your own typed questions per result, tone, same-story grouping, who published first
Rate limit10 queries/second 10 requests/second; 50 with a monthly plan
SDKsPython, JavaScript/TypeScript, a CLI and OpenAI SDK compatibility OpenAPI 3.1; works with the official Exa, Tako and Perplexity SDKs
MCP serverYes, remote Yes, remote: api.typesearch.ai/mcp

Checked Sep 25, 2026 · Sources: docs.linkup.so/pages/documentation/platform/pricing, docs.linkup.so/pages/documentation/endpoints/search/referenc, docs.linkup.so/pages/documentation/endpoints/fetch/reference, docs.linkup.so/pages/documentation/development/rate-limits

How the parameters map

Each Linkup parameter and what it becomes on typesearch. You rewrite one request; your agent’s logic stays.

Linkup parameterStatusOn typesearch
qSamequery. Or up to five queries, judged together.
depth: flash, fast, standard, deepMappedmode: "ultra", "fast", "normal", "deep"
outputType: searchResultsSameresults: a ranked list, every result with its source and date.
outputType: sourcedAnswerLimitedWe don’t write answers: essential returns the key verbatim excerpts across results.
outputType: structuredMappedquestions: typed answers per result (boolean, choice, score).
fromDate, toDateMappedpublished_after, published_before, within the last 30 days.
includeDomains, excludeDomainsLimitedinclude_domains, exclude_domains, up to 20 each.
maxResultsSamemax_results, up to 50.
includeImagesNot supportedNo images in results.
results[]: name, url, contentMappedresults[]: title, url, snippet, highlights — plus published_at and source

What you gain

  • The publication time and outlet on every result — Linkup’s search results don’t include them
  • $1.40 per 1,000 fast searches and $5.60 per 1,000 deep, against $5 and $50
  • A calibrated relevance probability on every result
  • Tone, same-story grouping and date windows built for news
  • Works with the Exa, Tako and Perplexity SDKs

When Linkup is the better fit

We’d rather you pick right the first time. Keep Linkup for these:

  • You search the whole web, not only news.
  • You want the API to write a sourced answer.
  • You need the full text of pages (Linkup Fetch).

The migration

The whole migration

Before and after: the request, the key header and the fields you read. Everything else in your code stays.

import requests
 
-r = requests.post("https://api.linkup.so/v1/search",
- headers={"Authorization": f"Bearer {LINKUP_API_KEY}"},
- json={"q": "lithium royalties in Chile", "depth": "standard", "outputType": "searchResults", "fromDate": "2026-09-18"},
-).json()
+r = requests.post("https://api.typesearch.ai/v1/search",
+ headers={"Authorization": f"Bearer {TYPESEARCH_API_KEY}"},
+ json={"query": "lithium royalties in Chile", "days": 7, "max_results": 20, "mode": "normal"},
+).json()
 
-for a in r["results"]:
- print(a["name"], a["url"], a["content"])
+for a in r["results"]:
+ print(a["title"], a["url"], a["published_at"], a["source"], a["score"])
beforeafter

Switching from Linkup

How is typesearch different from Linkup?

Linkup searches the web and returns extracted text, sourced answers or structured output. typesearch searches the news: every result carries its outlet and publication time, a calibrated probability, and — in normal and deep — it was read and verified.

How much does typesearch cost compared with Linkup?

Fast: $1.40 per 1,000 on typesearch, against $5 (Search, standard depth). Normal: $2.20 per 1,000 on typesearch, against $5 (Search, standard depth). Deep: $5.60 per 1,000 on typesearch, against $50 (Search, deep depth). Results served from the cache are free, and there are no seats or minimums.

How do I switch from Linkup?

Rewrite one request: the endpoint, the key header and a few parameter names change — see the table above. The fields you read map one to one: name → title, content → snippet and highlights (plus published_at and source, which Linkup doesn’t return).

When should I stay with Linkup?

If you need the whole web beyond news, answers written by the API, or full-page fetch. You can also use both: typesearch for what your agent searches now, Linkup for the rest.

Switch from Linkup

A key in a minute, $5 in free credit, one request to rewrite.