为 GEO 而生的 API

一个 API，提供 GEO 所需的全部分析数据 — 7 大引擎的真实浏览器答案采集、答案与来源的因果分析、GEO 监测，还在持续扩展。按国家，结构化 JSON。

ChatGPT
Gemini
Perplexity
Google AI Overviews
Google AI Mode
Naver AI Brief
Naver AI Mode

2,000 免费积分 · 无需信用卡

querying.ai/dashboard/playground

Response

COMPLETED · 1ad65a0f-…

COMPLETED
CHATGPT10.5s2 credits6 sources

Searched for

how AI search engines choose sources to cite retrieval ranking authority relevance

AI search engines generally choose citations through a retrieval-and-selection pipeline, not by simply picking the highest-ranking web page like a traditional search engine. The exact algorithms are proprietary and vary by product, but the broad process looks like this: answerbench.org

  1. Find candidate sources
  • The system first gathers potentially relevant material from search indexes, web crawls, licensed databases, or other retrieval systems.
  • A user question may be rewritten into multiple related searches so the system can find different angles of the answer. bluefrog.ai

  1. Match sources to the question AI systems look for sources whose content actually answers the user’s intent, often using semantic matching rather than only keyword matching. A page about “best running shoes for flat feet” may be preferred over a general shoe article because it contains the specific information needed. thestacc.com

  2. Score reliability and usefulness Common signals include:

  • Relevance: Does the source directly support the claim being made?
  • Authority: Is the source credible for this topic?
  • Freshness: Is it current enough, especially for news, prices, laws, or software?
  • Factual clarity: Does it provide specific, verifiable information?
  • Extractability: Can the system easily identify a passage that supports the answer? lightspacelabs.com

  1. Select evidence for specific claims The system is usually not asking “which website is the best overall?” It is asking something closer to: “Which source best supports this particular sentence?” A government page might be chosen for a legal fact, a research paper for a scientific claim, and a company’s documentation for a product feature. answerbench.org

  2. Generate the answer and attach citations After selecting useful passages, the AI produces a response and links citations to the claims those sources support. Some systems cite many sources; others prefer fewer sources that they rely on more heavily. arxiv.org

A few things that often surprise people:

  • The top Google result is not guaranteed to be cited. AI systems may choose a lower-ranked page if it provides a clearer or better-supported answer. lightspacelabs.com
  • Being authoritative is not enough. A highly reputable site can be skipped if the relevant information is buried, vague, outdated, or difficult for the system to extract. answerlab.au
  • Citations are not a perfect audit trail. A citation means the system used or found the source relevant, but it does not automatically mean every statement in the answer is fully verified by that source. answerbench.org

A simple mental model: AI search first finds possible evidence, then chooses the evidence that best supports the answer it wants to give. The winning source is often the one that is both trustworthy and easy to use as evidence. bluefrog.ai

Sources

  1. 1How AI Answer Engines Choose Which Sources to Cite — AnswerBenchhttps://answerbench.org/articles/how-ai-answer-engines-choose-sources
  2. 2How do AI assistants decide which sources to cite? | Bluefroghttps://bluefrog.ai/answers/assistants-choose-which-sources-to-cite/
  3. 3How AI Search Engines Choose Sources to Citehttps://thestacc.com/blog/how-ai-search-engines-cite-sources/
  4. 4How AI Search Engines Decide Which Sources to Cite | Lightspace Labs Blog | Lightspace Labshttps://www.lightspacelabs.com/blog/how-ai-search-engines-decide-which-sources-to-cite
  5. 5From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platformshttps://arxiv.org/abs/2604.25707
  6. 6How AI Search Engines Decide Which Sources to Cite | AnswerLabhttps://answerlab.au/blog/how-ai-decides-citations

看到答案，知道原因，持续追踪。

一个 API，覆盖 GEO 的三个层面：采集用户真实看到的 AI 答案，追溯是哪些来源塑造了答案，并持续计分。

Answers

ChatGPT、Gemini、Perplexity、Google AI 与 Naver AI 的真实消费者答案，按国家返回结构化 JSON。

GEO Research

把答案和引用回传，即可看到究竟是哪个来源的哪个段落塑造了哪句话——每个判定都附带证据。

Monitors

定期运行保存的提示词集，为品牌露出与引用计分 — 随时间衡量你在 AI 答案中的份额。

7 个引擎，1 个 API — 实时状态

覆盖所有引擎、所有地区，支持大规模调用。引擎状态基于实测数据 — 有问题会如实显示。

ChatGPTGoogleGeminiPerplexityNaver

每个界面是什么，又会返回什么

不是把一个模型包装七次，而是七个各不相同的消费者界面。每个返回自己的结构化数据，下面的字段名就是落进你 Webhook 里的东西。

ChatGPT

就是人人都能免费用的那个 ChatGPT，在开启网页搜索的状态下作答。所以返回的不只是正文 — 还包括它作答前实际发出的搜索查询（fan-out）、支撑答案的引用卡片，以及购物卡片。真正生成答案的模型会写进 `model`，你始终知道自己测的是什么。

textsourcesmarkdownsearchQueriesshoppingCardsmodel

Gemini

是消费者版 Gemini 应用，不是 Gemini API。每个来源都带有谷歌自己的 0–100 grounding 置信度，因此可以给引用加权，而不是一视同仁。

textsourcesmarkdownmodel

Perplexity

除 Perplexity 的答案外，还返回这里最丰富的结构化数据：其搜索模型实际发出的查询、推荐的追问，以及媒体、购物、地点和酒店模块。

textsourcesmarkdownsearchQueriesrelated_queriesvideosimagesshopping_cardsplaceshotels

Google AI Overviews

谷歌搜索结果页顶部的 AI Overview 模块。它是条件性的 — 谷歌没有生成概览的查询会如实告知 — 同一次抓取的自然结果和 People Also Ask 会一并返回。

aiovervieworganicResultspeopleAlsoAsk

Google AI Mode

谷歌 AI Mode 标签页，是对话而非摘要模块。完整答案同时写入 `text` 与 `markdown`（页面装饰已剔除），并附上谷歌引用的全部来源。

textsourcesmarkdown

Naver AI Brief

Naver 综合搜索里的 AI 브리핑 模块。Naver 只为它认为值得简报的查询生成，所以空简报是真实答案而非失败 — 模块下方的网页文档无论如何都会一起返回。

textsourcesmarkdownorganicResultsrelatedQuestions

Naver AI Mode

Naver 的 AI 탭 — 常驻、对话式，也是唯一会返回含价格、折扣率、评分与配送信息的韩国购物卡片的界面。

textsourcesmarkdownproducts

为什么不直接调用 LLM API？

调用供应商 API 得到的是模型输出 — 不是用户在屏幕上看到的内容。

消费者界面 ≠ LLM API

ChatGPT 消费者应用会加入搜索增强、引用、区域路由和实时检索 — 这些 OpenAI API 没有。GEO 和 AEO 分析需要的是「用户实际看到什么」而非「模型能生成什么」。querying.ai 采集真实消费者界面。

答案之外的结构化数据

向 Perplexity 提一个问题会返回十个字段，其中包括它的搜索模型实际发出的查询 — 这是最接近「AI 认为你的品牌是什么」的记录。ChatGPT 返回搜索 fan-out 和购物卡片；Naver AI 返回含价格、折扣率、评分与配送的韩国商品卡片。

同一条提示词，换个国家就是另一个答案

在首尔问跑鞋推荐和在芝加哥问跑鞋推荐，品牌不同、商店不同、引用来源也不同。每个任务都接收 `country` 并从该市场发起调用，所以你为 KR 报出的排名，就是韩国用户真正看到的排名。

空答案也是一种结论

Google AI Overviews 和 Naver 的 AI 브리핑 都是条件性的：很多查询根本不会生成摘要。你所在品类的核心查询没有 AI 答案，这件事本身就是有价值的 GEO 结论。所以我们如实上报 — 不伪装成故障，也不为了填满字段而编造。

成本最高低 85%

OpenAI Responses API (web search)：~$10/1k calls。querying.ai ChatGPT：Basic $4/1k，Max $1.90/1k。并非同一产品，但对需要消费者界面数据的团队而言，成本差距显而易见。失败任务不收费。

信任之前可以先核验的状态

引擎健康度由最近 30 分钟的真实任务结果计算，而不是合成探测 — 合成探测可能在客户流量大面积失败时依然通过。状态按引擎公开在 status.querying.ai，你可以自己核对采集数据那天哪些界面是正常的。

这些团队在用

为所有需要理解 AI 搜索的团队提供统一的结构化数据源。

GEO 与 AEO 监测

按引擎、国家和提示词追踪品牌、产品和竞争对手在 AI 搜索中的展现情况。

竞争情报

实时查看 AI 引擎在你的市场中引用了哪些品牌、推荐了哪些产品。

代理商仪表盘

通过批量 API 和 Webhook 同时监控数十个客户的 AI 搜索表现。

研究与分析

利用结构化数据研究各市场的 AI 搜索行为，服务于学术研究、内容策略和 SEO 分析。

提交任务，答案自动送达。

所有任务都是异步的 — 因为引擎响应需要数秒。提交后获得 id，结果通过 Webhook 以 JSON 推送。

01提交任务
curl -X POST https://api.querying.ai/v1/async/task \
  -H "Authorization: Bearer vt_live_…" \
  -H "Content-Type: application/json" \
  -d '{
    "taskType": "GEMINI",
    "payload": { "prompt": "best wireless earbuds 2026" },
    "webhook": { "url": "https://yours.app/hooks/querying" }
  }'
02Webhook 接收
{
  "task": {
    "id": "8f2c1e40-…",
    "taskType": "GEMINI",
    "status": "COMPLETED",
    "createdAt": "2026-07-17T04:12:00.000Z"
  },
  "credits": { "creditsToCharge": 1, "creditsCharged": 1 },
  "response": {
    "text": "The best wireless earbuds in 2026 are …",
    "sources": [
      { "position": 1,
        "url": "https://example.com/review",
        "label": "Best earbuds, reviewed" }
    ],
    "timing": { "totalMs": 7400 }
  }
}

端点不可用时自动退避重试 5 次。 查看文档 ↗

按量付费，没有意外账单

套餐越大积分越便宜 — Max 低至每 1,000 积分 $0.95。失败任务自动退款。

Basic
$20/month
10,000 credits included

A single product's tracking, or a build you're still shaping.

≈ 5,000–10,000 tasks / month
  • 10 concurrent tasks
  • Every engine we serve
  • Every region we serve
  • Webhooks + polling
  • Email support
Recommended
Pro
$200/month
190,000 credits included

A brand tracked daily across engines, countries and prompts.

≈ 95,000–190,000 tasks / month
  • 25 concurrent tasks
  • Everything in Basic
  • Batch submission
  • Priority support
Scale
$500/month
500,000 credits included

Several brands, or one brand tracked wide and deep.

≈ 250,000–500,000 tasks / month
  • 50 concurrent tasks
  • Everything in Pro
  • Usage review on request
  • Priority support
Max
$1000/month
1,050,000 credits included

An agency or platform running many brands at once.

≈ 525,000–1,050,000 tasks / month
  • 100 concurrent tasks
  • Everything in Scale
  • Usage review on request
  • Priority support
Enterprise
Custom
Volume pricing

Committed volume, invoicing, and terms that fit procurement.

  • Everything in Max
  • Custom engine mix
  • Invoice billing
  • Shared support channel
Talk to us
Negotiated

Task estimates vary by engine because each engine uses 1–2 credits.

See what a credit buys, per engine →