Compared with NewsData.io
The NewsData.io alternative for AI agents
NewsData.io sells credits for a huge catalog and a long archive. typesearch sells judged, current results for agents: a calibrated relevance probability on each, the top ones read before they’re ranked, and typed answers in the same call — from $1.40 per 1,000 searches, with no monthly plan.
Checked Sep 25, 2026 · A news API with a 10-year archive and AI tags
At the same volume
Basic · 20,000 requests a month
$28/ month
typesearch, fast mode
NewsData.io: $199.99−85%
$10 per 1,000 · 20,000 credits a month
Professional · 50,000 requests a month
$70/ month
typesearch, fast mode
NewsData.io: $349.99−79%
$7 per 1,000 · 50,000 credits a month
Corporate · 1,000,000 requests a month
$1,400/ month
typesearch, fast mode
NewsData.io: $1,299.998% less on NewsData.io
$1.30 per 1,000 · 1,000,000 credits a month
NewsData.io counts credits: a latest-news search is 1 credit and returns up to 50 articles; an archive search costs 5. Extra credits are $0.006 each; annual billing is cheaper. typesearch returns up to 50 judged results per search, with no plan: the same price at any volume.
Checked Sep 25, 2026 · Sources: newsdata.io/pricing
Side by side
What NewsData.io publishes, next to what typesearch does. Each of their facts links to where we read it.
Checked Sep 25, 2026 · Sources: newsdata.io/pricing, newsdata.io/free-news-api, newsdata.io/documentation, github.com/newsdataapi/newsdata.io-mcp
How the parameters map
Each NewsData.io parameter and what it becomes on typesearch. You rewrite one request; your agent’s logic stays.
| NewsData.io parameter | Status | On typesearch |
|---|---|---|
| q | Same | query. Or up to five queries, judged together. |
| qInTitle, qInMeta | Limited | We judge title and standfirst, and read the top articles in normal and deep. |
| country, language | Limited | Query in the language you want, or restrict to regional outlets with include_domains. |
| category | Mapped | sections: the outlet’s own section, or the start of the URL path. |
| domain, domainurl | Mapped | include_domains, up to 20. |
| excludedomain | Mapped | exclude_domains, up to 20. |
| timeframe | Mapped | days (1 = the last 24 hours), or published_after. |
| from_date, to_date (archive) | Limited | published_after, published_before, within the last 30 days. |
| size, page | Limited | max_results, up to 50. No pagination. |
| removeduplicate | Mapped | dedupe: true groups the same story, with the duplicates attached. |
| sentiment | Mapped | tone: true — positive, neutral or negative toward your query. |
| full_content | Limited | Never the full article: verbatim highlights in normal and deep. |
| results[]: title, link, description, pubDate, source_name | Mapped | results[]: title, url, snippet, published_at, source |
What you gain
- No $199.99 entry plan: pay as you go, from $1.40 per 1,000 searches
- A calibrated relevance probability on every result
- Your own typed questions answered per article, on every request
- Tone and same-story grouping included, not tied to a plan
- Up to five queries per request, judged together
When NewsData.io is the better fit
We’d rather you pick right the first time. Keep NewsData.io for these:
- You need years of archive: up to 10 years on Corporate; our index keeps 30 days.
- You need the full article text, or AI tags for regions and organizations.
- You filter by country or language across 200+ countries today.
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://newsdata.io/api/1/archive",- headers={"X-ACCESS-KEY": NEWSDATA_API_KEY},- params={"q": "lithium royalties in Chile", "from_date": "2026-09-18", "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["results"]:- print(a["title"], a["link"], a["pubDate"], a["source_name"])+for a in r["results"]:+ print(a["title"], a["url"], a["published_at"], a["source"], a["score"])
Switching from NewsData.io
How is typesearch different from NewsData.io?
NewsData.io filters a large catalog by keyword, country, language and category, with AI tags and sentiment on higher plans. typesearch judges every result for your query — a calibrated probability, the top ones read — and answers your own typed questions per article.
How much does typesearch cost compared with NewsData.io?
At the volume of NewsData.io’s Basic plan (20,000 requests a month), typesearch costs $28 in fast mode, against $199.99. At the volume of NewsData.io’s Professional plan (50,000 requests a month), typesearch costs $70 in fast mode, against $349.99. At the volume of NewsData.io’s Corporate plan (1,000,000 requests a month), typesearch costs $1,400 in fast mode, against $1,299.99. Results served from the cache are free, and there are no seats or minimums.
How do I switch from NewsData.io?
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, pubDate → published_at, source_name → source.
When should I stay with NewsData.io?
If you need years of archive, full article text, or a filter for one of 206 countries today. You can also use both: typesearch for what your agent searches now, NewsData.io for the rest.
Keep comparing
Other comparisons
Use cases
Switch from NewsData.io
A key in a minute, $5 in free credit, one request to rewrite.