Compared with Linkup
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.
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 parameter | Status | On typesearch |
|---|---|---|
| q | Same | query. Or up to five queries, judged together. |
| depth: flash, fast, standard, deep | Mapped | mode: "ultra", "fast", "normal", "deep" |
| outputType: searchResults | Same | results: a ranked list, every result with its source and date. |
| outputType: sourcedAnswer | Limited | We don’t write answers: essential returns the key verbatim excerpts across results. |
| outputType: structured | Mapped | questions: typed answers per result (boolean, choice, score). |
| fromDate, toDate | Mapped | published_after, published_before, within the last 30 days. |
| includeDomains, excludeDomains | Limited | include_domains, exclude_domains, up to 20 each. |
| maxResults | Same | max_results, up to 50. |
| includeImages | Not supported | No images in results. |
| results[]: name, url, content | Mapped | results[]: 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"])
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.
Keep comparing
Other comparisons
Use cases
Switch from Linkup
A key in a minute, $5 in free credit, one request to rewrite.