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

Use casesRisk and compliance

Adverse media and regulatory watch, with evidence.

Screen counterparties and suppliers for adverse media, watch regulators and supply-chain disruptions, and keep a link and a verbatim quote for every flag — in local languages, from local press.

Free API keyThe request

POST /v1/searchmode: "deep" · $5.60 per 1,000 queries

The problem

Screening needs recall, precision and a paper trail

Adverse media screening — for KYC, onboarding a supplier or reviewing a partner — fails in two directions: it misses the local story that matters, or it drowns analysts in name collisions and irrelevant mentions.

And every flag needs evidence an auditor can follow: where it was published, when, and what exactly it said.

How it works

  • 01

    The entity and the risk, together

    Several queries per request: “Globex Logistics investigation”, “… fraud”, “… sanctions”. Judged together, each result tagged with its query.

  • 02

    Deep for onboarding

    Deep widens the topic with synonyms and acronyms, reads 8 articles and returns verbatim highlights — the quote you keep as evidence.

  • 03

    A yes/no you can threshold

    Ask “does it report an allegation, investigation, sanction or conviction involving the entity?” and get a calibrated probability per article, plus the risk category.

  • 04

    Then watch it daily

    Once screened, a daily fast search per entity with days: 1 keeps the file current at a fraction of the cost.

API

The request

One request does it. The same parameters work over HTTP, with the SDKs and through the MCP server.

What it costs

Recommended · deep$5.60 per 1,000 queries

Deep reads 8 articles per query and returns verbatim highlights: the evidence for each flag.

Also good · fast$1.40 per 1,000 queries

Fast ($1.40) for the daily watch after onboarding: headlines and standfirsts, about a second per request.

An example month

1,000 entities watched daily in fast mode for 30 days

30,000 queries in fast mode ≈ $42

List prices from our pricing page. Each query in a multi-query request counts as one search; identical requests within 10 minutes are free.

curl https://api.typesearch.ai/v1/search \
  -H "Authorization: Bearer $TYPESEARCH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": ["Globex Logistics investigation", "Globex Logistics fraud", "Globex Logistics sanctions"],
    "mode": "deep",
    "days": 30,
    "max_results": 25,
    "questions": {
      "adverse": {
        "type": "boolean",
        "instructions": "Does the article report an allegation, investigation, sanction or conviction involving Globex Logistics?"
      },
      "category": {
        "type": "choice",
        "instructions": "What is the main risk reported?",
        "criteria": {
          "fraud": null,
          "corruption": null,
          "sanctions": null,
          "environmental": null,
          "labor": null,
          "other": null
        }
      }
    }
  }'

What you get back

  • answers: your typed questions per article (adverse or not, risk category)
  • highlights: verbatim excerpts of up to 25 words, from the article text
  • Title, URL, source and publication time: the paper trail
  • Local and regional press, in the language it was written in

When to use something else

  • You need sanctions lists, PEP databases or court records: we cover news, not registries.
  • You need adverse media going back years: our index keeps a rolling 30 days; use an archive for historical screening.
  • You need a decision, not evidence: our answers are inputs for your analysts and rules, not a compliance verdict.

One result, trimmed

{
  "title": "Regulator opens probe into Globex Logistics billing",
  "url": "https://eupolicy.example/enforcement/globex-probe",
  "source": "EU Policy",
  "published_at": "2026-09-22T07:40:00Z",
  "score": 0.93,
  "highlights": ["The authority said it had opened a formal investigation into Globex Logistics"],
  "answers": {
    "basis": "article",
    "values": {
      "adverse": { "type": "boolean", "probability": 0.94 },
      "category": { "type": "choice", "choice": "fraud", "confidence": 0.71 }
    }
  }
}

Questions

Can typesearch replace an adverse media screening provider?

It can be the news layer of your own screening: recall across local press, a calibrated probability per article and a quote for every flag. It doesn’t include sanctions lists, PEP databases or case management.

How do you handle name collisions?

Put the context in the query and in a typed question — “involving Globex Logistics, the freight company” — and threshold on the probability. In deep mode the article is read, so the answer is based on the text.

Does it cover supply-chain disruptions?

Yes: strikes, fires, floods or port closures are news. Query by supplier, site or region, and ask a typed question for the kind of disruption.

What does it cost?

Screening one entity with three deep queries costs 3 × $5.60 per 1,000 — well under a cent. 30,000 queries in fast mode ≈ $42 for the daily watch.

Keep reading

Comparisons

Alternatives

Use cases

Products

Docs

Build it this afternoon.

Get a key with $5 in free credit, run the request above and see what comes back.

Free API keyTalk to sales