NewYour Exa or Tako SDK, 5× cheaper.

Search for AI agents.Faster, and 5× cheaper.

Our own continuously refreshed index, a calibrated relevance score on every result, and drop-in compatibility with the Exa and Tako SDKs. Keep your code. Cut your search bill by 80%.

$1.40 per 1,000 searches · Exa and Tako list at $7

Output

    Sample outputRelevance is a calibrated probability. Between 0.35 and 0.65 we say “undecided” instead of guessing.

    Speaks the SDKs you already ship

    • exa-pyPython
    • exa-jsTypeScript
    • takoPython · JS
    • perplexityPython · JS
    • OpenAPI3.1
    • RESTJSON · SSE

    The numbers

    Cheaper at every depth. Faster where it counts.

    Public list prices, and measurements from our own test suite. No cherry-picked benchmarks.

    List price per 1,000 requests, USDLower is better
    List price per 1,000 requests, USD
    typesearchExaTako
    Search$1.40$7$7
    Deep search$2.40$12–15$12
    Contents · per 1k pages$0.20$1$1

    Prices: exa.ai/pricing and tako.com/pricing, September 2026. Speed and compatibility: our internal test suite. Methodology on request.

    Do the math

    Your search bill, at a fifth.

    Slide to your monthly volume. List prices, no asterisks.

    Published list prices on exa.ai/pricing and tako.com/pricing, checked September 2026, before free tiers. Deep search uses Exa’s lowest deep tier.

    10K1M100M
    • Exa$7,000 / month
    • Tako$7,000 / month
    • typesearch$1,400 / month

    You keep

    $67,200a year

    5× cheaper
    Start saving — get a key

    The index

    Our own index. Not a reseller’s wrapper.

    We crawl, refresh and rank our own index. Sources are re-read every few minutes from their news sitemaps and feeds, so what’s published at 9:02 is searchable by 9:05 — in the language it was written.

    • Freshness you can filter byEvery result carries its publication time and source. Filter by the hour, not the week.
    • Deep where others are thinLocal and regional press across Latin America and Europe — not just the English-language web.
    • Publisher-safe by designWe honor robots.txt, return short verbatim excerpts, and never redistribute full articles.
    Live ingestGET /v1/sources
    • 09:05:12elpais.comESindexed 3s ago
    • 09:05:09reuters.comENindexed 6s ago
    • 09:05:07lanacion.com.arESindexed 8s ago
    • 09:05:04lemonde.frFRindexed 11s ago
    • 09:05:02valor.globo.comPTindexed 13s ago
    • 09:04:58eltiempo.comESindexed 17s ago
    • 09:04:55handelsblatt.comDEindexed 20s ago
    • 09:04:51infobae.comESindexed 24s ago
    • 09:04:49ft.comENindexed 26s ago
    • 09:04:46elespectador.comESindexed 29s ago
    • 09:04:42corriere.itITindexed 33s ago
    • 09:04:40folha.uol.com.brPTindexed 35s ago
    • 09:05:12elpais.comESindexed 3s ago
    • 09:05:09reuters.comENindexed 6s ago
    • 09:05:07lanacion.com.arESindexed 8s ago
    • 09:05:04lemonde.frFRindexed 11s ago
    • 09:05:02valor.globo.comPTindexed 13s ago
    • 09:04:58eltiempo.comESindexed 17s ago
    • 09:04:55handelsblatt.comDEindexed 20s ago
    • 09:04:51infobae.comESindexed 24s ago
    • 09:04:49ft.comENindexed 26s ago
    • 09:04:46elespectador.comESindexed 29s ago
    • 09:04:42corriere.itITindexed 33s ago
    • 09:04:40folha.uol.com.brPTindexed 35s ago
    news sources in our registry
    2,800+
    refresh cycle per source
    5 min
    to first results
    ~1 s
    queries per request
    5

    Beyond ten blue links

    Everything your agent needs from the news, in one call.

    • Tone, relative to your query

      Positive, neutral or negative about what you asked — per result and per source. One scale for news, blogs and social.

    • One story, one result

      The same wire story told by ten outlets collapses into one result, with the duplicates attached.

    • Who published first

      Coverage by day and by source, and who broke it. Computed from the index at no extra cost.

    • Essentials, never invented

      Up to three verbatim excerpts from different sources. We quote; we don’t write. Zero hallucinated summaries.

    • Hard cost caps

      Set a budget per request. We return what fits and mark the response incomplete — never a surprise invoice.

    • Live site search

      Search any site right now: its homepage, the sections worth reading and its own search box, in parallel.

    Migration

    Switch in two lines. Keep everything else.

    One compatibility layer per provider: same parameters, same response shape, same errors. Point your official SDK at us and ship.

    • Same shapes, same errorsResponses and error formats match each provider. Your parsing code doesn’t change.
    • Nothing breaks silentlyParameters we don’t support are accepted and reported in X-Compat-Warnings instead of failing the request.
    • Our extras ride alongTone, essentials, modes and cost caps travel in one extra field of the same request.
    Read the migration guide
    from exa_py import Exa
     
    -exa = Exa(api_key=EXA_API_KEY)
    +exa = Exa(api_key=TYPESEARCH_API_KEY, base_url="https://api.typesearch.ai/compat/exa")
     
    results = exa.search("lithium royalties in Chile", num_results=10, type="fast")
    similar = exa.find_similar(results.results[0].url, exclude_source_domain=True)
    pages = exa.get_contents([r.url for r in results.results], highlights=True)
    beforeafter

    Production

    Boring where it matters.

    • Versioned contract

      /v1 only changes by adding. Anything breaking ships as /v2, with notice.

    • Quotas and limits per key

      Daily quotas and per-minute limits on every key, visible in real time through the usage API.

    • Errors you can program against

      RFC 9457 problem details, stable error codes and a request ID on every response.

    • Keys hashed at rest

      We store a hash, never your key. Rotate and revoke anytime.

    • OpenAPI 3.1

      The contract is generated from the same schemas that validate every request.

    • Streaming built in

      JSON or server-sent events on every search endpoint, with partial results as they land.

    Running search at scale?

    Volume pricing, custom source coverage, dedicated support and SLAs. Tell us what you pay today — we’ll show you what you’d pay here.

    Talk to sales

    Questions, answered

    Is it really 5× cheaper?

    Yes, on list price. Search is $1.40 per 1,000 requests; Exa and Tako both list $7. Deep search is $2.40 against $12–15, and contents $0.20 against $1 per 1,000 pages. Put your own volume in the calculator above.

    Will my Exa or Tako code break?

    It shouldn’t. We run the official SDKs — Python and JavaScript — against our compatibility layers: 25 of 25 test cases pass by changing only the base URL and the key. Anything we don’t support is accepted and reported in a response header, not thrown as an error.

    What’s in the index?

    News and editorial content, crawled and refreshed by us every few minutes, with deep coverage of local and regional press in Latin America and Europe. The sources endpoint returns the live list.

    Do you generate answers or summaries?

    No, on purpose. We return evidence: ranked, verified, with verbatim excerpts. If you need prose, your model writes it — grounded in results that can’t be hallucinated.

    What’s the catch?

    Two honest limits: we return short excerpts instead of full page text, and we don’t offer people, company or academic-paper indexes. If those are core to your product, keep them where they are and move the rest of your search to us.

    Can I try it for free?

    Yes. Every new account gets $5 in free credit, about 3,571 searches on any endpoint, valid for 30 days. No card needed. Your first top-up gets 20% extra, up to $20.

    Stop paying 5× for search.

    Get a key in a minute. Point your SDK at us. Watch the invoice shrink.