Retrieval API · v2 · 1.2T pages indexed

Search,
sifted for AI.

Fast Retrieval & Search API for AI Agents

The retrieval layer for agents that need precise, fresh, structured web
context — sub-180ms, neural-ranked, and built for production.

Playground

One endpoint.
Four modes of retrieval.

Pick the latency / depth tradeoff per call. Same schema, same auth, radically different shapes of context for your agent.

FAST
ready · live via SiftQ
No results returned.

Trusted by teams building the next generation of agents

HEXLANENORTHWAVEQuill&Co◣ STRATAPINNACLE/AIarclight⌬ tesseraFERRO·LABSMarginalia▲ APEX
Benchmarks

Best-in-class accuracy,
at sub-second latency.

Evaluated against the most demanding retrieval benchmarks and head-to-head with leading providers. Numbers below are 30-day rolling averages.

FRAMES arXiv:2409.12941
accuracy @ k=10
SiftQ
56.1%
Perplexity
44.5%
Brave
21.6%
Tip-of-Tongue
recall
SiftQ
56.4%
Perplexity
36.7%
Brave
19.3%
Seal-0 arXiv:2410.09078
long-tail accuracy
SiftQ
38.4%
Perplexity
34.5%
Brave
8.2%
01
Accuracy

Leads across FRAMES, Tip-of-Tongue, and Seal-0 — the three retrieval evals that punish shallow indexers.

02
Latency

SiftQ Fast returns ranked results under 180ms at p50, faster than any other major retrieval provider.

03
Verticals

Specialized indexes for companies, people, code, papers, filings, and news — not just one generic crawl.

Search API

Structured output,
built into the call.

Pass a JSON schema. Get typed records back. No second LLM hop, no parser-of-parsers, no extraction prompt drift.

  • Typed fields with schema validation
  • Aggregations across 70M+ companies, 480M+ people, 12M+ repos
  • Stream results as they're enriched
Read the SiftQ API schema reference →
POST /v2/search · structured
"schema": {
  "companies": [{
    "name": string,
    "ceo": string,
    "founded": int
  }]
}

// → results
{
  "companies": [
    { "name": "General Electric",
      "ceo":  "Larry Culp",
      "founded": 1892 },
    { "name": "RTX",
      "ceo":  "Christopher Calio",
      "founded": 2020 },
    { "name": "Boeing",
      "ceo":  "Kelly Ortberg",
      "founded": 1916 }
  ]
}
Web indexes

Industry-leading indexes,
built for agents.

Dedicated, freshness-tuned indexes for every retrieval shape your agent needs: people, companies, code, docs, filings, papers, news.

Browse the SiftQ index catalog →
<180ms
p50 latency · Fast mode
people480M
companies70M
repositories12M
research papers84M
SEC filings4.1M
news articles · 24h2.6M
en.wikipedia.org / Boeing
Highlights: ON

The Boeing Company is an American multinational corporation that designs, manufactures, and sells airplanes, rotorcraft, rockets, satellites, and missiles worldwide. The company also provides leasing and product support services. Boeing is among the largest global aerospace manufacturers; it is the fifth-largest defense contractor in the world based on 2022 revenue.

1,084 chars returned↓ 91% vs full page
Highlights & content

Pay for signal,
not for HTML.

Return only the spans of a page that match the query. Cut your context window cost, and ship faster agents that don't drown in chrome and footer junk.

90%
average token reduction vs raw fetch
Get SiftQ page contents →
Security & trust

Security posture
without overclaiming.

Review data terms

Retention options

Default logs support debugging and abuse prevention. Shorter retention or special handling can be reviewed for eligible enterprise customers.

Security review

We can share security documentation and technical architecture notes as part of enterprise evaluation. Formal reports are provided only when available.

Access controls

API keys stay server-side in the product flow. Team access, SSO, and dedicated deployment options are handled by agreement.

Customers

Trusted by
world-class teams.

View all customer stories →
SiftQ's coverage on long-tail technical papers is the only one that consistently surfaces what our researchers ask for. It quietly replaced four other tools.
AAAnjali AroraHead of AI · Hexlane
We swapped retrieval providers in an afternoon. p50 dropped from 920ms to 174ms, and the agent's grounding scores went up double digits.
JMJonas MehlFounding eng · Northwave
The structured output mode collapsed a five-step enrichment pipeline into one call. We deleted more code than we wrote that quarter.
RPRohan PatelCTO · Strata
Highlights alone paid for the contract. We dropped LLM token spend by 58% and shipped a faster product the same week.
LCLena ChuCEO · Quill & Co
Their long-tail recall on Seal-0 was the deciding factor. For an agent that has to be right about obscure things, SiftQ was the only one that held up.
DKDaniel KovacsResearch lead · Marginalia
Models are only as good as what they retrieve. SiftQ gave us the high-quality grounding signal we couldn't assemble in-house at any price.
MIMei IwasakiChief scientist · Tessera

Search built
for your AI.

The fastest, most accurate retrieval API on the public web. Give your agents the context they need — and only that.