Compared with NewsCatcher
The NewsCatcher alternative for AI agents
NewsCatcher is an enterprise news data platform with deep NLP. typesearch is a self-serve news search for agents: public prices from $1.40 per 1,000 searches, a key in a minute, a calibrated relevance probability on every result and typed answers in the same call.
Checked Sep 25, 2026 · An enterprise news API with rich NLP
No public price
NewsCatcher doesn’t publish News API prices: a 7-day trial, then “contact us”, and production use is on Enterprise plans. typesearch is pay as you go, with the price of every mode on our pricing page.
From $1.40 per 1,000 searches on typesearch · no seats or minimums
Checked Sep 25, 2026 · Sources: newscatcherapi.com/pricing
Side by side
What NewsCatcher publishes, next to what typesearch does. Each of their facts links to where we read it.
Checked Sep 25, 2026 · Sources: newscatcherapi.com/pricing, newscatcherapi.com/docs/news-api/get-started/subscription-pl, newscatcherapi.com/news-api, newscatcherapi.com/docs/news-api/api-reference/overview
How the parameters map
Each NewsCatcher parameter and what it becomes on typesearch. You rewrite one request; your agent’s logic stays.
| NewsCatcher parameter | Status | On typesearch |
|---|---|---|
| q | Same | query. Or up to five queries, judged together. |
| search_in | Limited | We judge title and standfirst, and read the top articles in normal and deep. |
| lang, countries | Limited | Query in the language you want, or restrict to regional outlets with include_domains. |
| sources, not_sources | Mapped | include_domains, exclude_domains, up to 20 each. |
| from_, to_ | Mapped | published_after, published_before, within the last 30 days. |
| sort_by | Limited | Ranked by a calibrated relevance probability; published_at to sort by date. |
| page_size, page | Limited | max_results, up to 50. No pagination. |
| exclude_duplicates, clustering_enabled | Mapped | dedupe: true groups the same story, with the duplicates attached. |
| include_nlp_data (sentiment) | Mapped | tone: true — positive, neutral or negative toward your query. |
| ORG_entity_name, PER_entity_name… | Limited | Name the entity in the query, or ask a typed question about it per article. |
| x-api-token | Mapped | Authorization: Bearer <key> |
| articles[]: title, link, description, published_date, name_source | Mapped | results[]: title, url, snippet, published_at, source |
What you gain
- Public, pay-as-you-go prices and a key in a minute — no sales call
- A free credit to build with, not a 7-day trial
- A calibrated relevance probability on every result
- Your own typed questions answered per article, instead of fixed tags
- Works with the Exa, Tako and Perplexity SDKs
When NewsCatcher is the better fit
We’d rather you pick right the first time. Keep NewsCatcher for these:
- You need full article text and an archive back to 2019.
- You need entities, IPTC/IAB tags or embeddings on every article.
- You pull up to 1,000 articles per request into your own pipeline.
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.get("https://v3-api.newscatcherapi.com/api/search",- headers={"x-api-token": NEWSCATCHER_API_KEY},- params={"q": "lithium royalties in Chile", "from_": "2026-09-18", "page_size": 20},-).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": "fast"},+).json()-for a in r["articles"]:- print(a["title"], a["link"], a["published_date"], a["name_source"])+for a in r["results"]:+ print(a["title"], a["url"], a["published_at"], a["source"], a["score"])
Switching from NewsCatcher
How is typesearch different from NewsCatcher?
NewsCatcher sells news data under enterprise contracts, with entities, clustering and embeddings. typesearch is self-serve: public per-request prices, a calibrated probability on every result, the top ones read, and your own typed questions answered per article.
How much does typesearch cost compared with NewsCatcher?
NewsCatcher doesn’t publish News API prices: a 7-day trial, then “contact us”, and production use is on Enterprise plans. typesearch is pay as you go, with the price of every mode on our pricing page. Results served from the cache are free, and there are no seats or minimums.
How do I switch from NewsCatcher?
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: link → url, description → snippet, published_date → published_at, name_source → source.
When should I stay with NewsCatcher?
If you need full article text, an archive back to 2019, entity and IPTC tagging, or up to 1,000 articles per request. You can also use both: typesearch for what your agent searches now, NewsCatcher for the rest.
Keep comparing
Other comparisons
Use cases
Switch from NewsCatcher
A key in a minute, $5 in free credit, one request to rewrite.