# AI Citation Lead Extractor (`nextgen.api/spark-agent-commerce-ai-citation-lead-extractor`) Actor

See which domains Google AI Overview cites. Get a deduped lead table with citation counts, sample URLs, and the prompts that triggered each cite. Built for SEO agencies, PR, and competitor intel.

- **URL**: https://apify.com/nextgen.api/spark-agent-commerce-ai-citation-lead-extractor.md
- **Developed by:** [Logan Bryant](https://apify.com/nextgen.api) (community)
- **Categories:**
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $18.00 / 1,000 lead domain extracteds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## What is AI Citation Lead Extractor?

**See which domains Google AI Overview cites, then turn those sources into a deduped lead table.** Give it a batch of prompts. Get back unique domains with citation counts, sample URLs, and the prompts that triggered each cite — ready to export as CSV for outreach, competitor intel, or link prospecting.

This extracts **who gets cited**. It does not check whether *your* brand is cited. For that, use [AI Citation Monitor](https://apify.com/nextgen.api/spark-agent-commerce-ai-citation-monitor).

### What this Actor does

- Runs each prompt against Google search with AI Overview sources
- Parses cited URLs, aggregates by registrable domain
- Dedupes, counts, and keeps sample URLs plus originating prompts
- Caps the table with min\_citations and max\_results
- Runs on Apify: scheduling, dataset export (JSON / CSV / Excel), API, webhooks, integrations

### Who it is for

- SEO agencies building an AI-citation prospect list without an Ahrefs seat for a one-off
- PR teams seeing which publishers Google treats as sources on a topic
- B2B content teams finding which competitors own the Overview for their category

### How to use it

1. Paste 10-50 natural-language prompts (questions, not keyword lists).
2. Keep country US and language en unless you have a geo-specific brief.
3. Set min\_citations to 2 if you only want domains cited more than once.
4. Run. Export the default dataset.

#### Input example

```json
{
  "prompts": [
    "best AI chips for training large language models",
    "leading companies in generative AI infrastructure",
    "top SEO tools for link building in 2026"
  ],
  "country": "US",
  "language": "en",
  "min_citations": 1,
  "max_results": 100
}
```

#### Output example

```json
{
  "domain": "analyticsindiamag.com",
  "citation_count": 1,
  "sample_urls": [
    "https://analyticsindiamag.com/ai-trends/10-most-powerful-ai-chips-dominating-the-llm-race"
  ],
  "prompts_that_cited": [
    "best AI chips for training large language models"
  ]
}
```

### How much does it cost?

Pay per event. No monthly subscription.

| Event | Price |
| --- | --- |
| Actor start | $0.00005 per GB of memory |
| Lead domain extracted (dataset item) | $0.018 ($18 per 1,000 unique domains) |

A 50-domain table is about $0.90 plus a few cents to start. You are billed for domains written to the dataset, not for prompts that produced no AI Overview sources.

Live coverage is Google AI Overview only (not ChatGPT or Perplexity).

### Related Actors

| Actor | Use it when |
| --- | --- |
| [AI Citation Monitor](https://apify.com/nextgen.api/spark-agent-commerce-ai-citation-monitor) | Is MY brand cited in Google AI Overview? |
| AI Citation Lead Extractor (this one) | WHO does Google cite for these prompts? |

### FAQ

#### How is this different from Google Search Results Scraper?

The scraper returns raw SERP JSON. This Actor rolls that up into a deduped domain table with counts, sample URLs, and prompt attribution.

#### Can I export CSV?

Yes. Open the run dataset in Console and export CSV, or use the dataset API.

#### What if an Overview has no sources?

That prompt contributes zero domains. It does not fail the run.

# Actor input Schema

## `prompts` (type: `array`):

Natural-language queries to extract cited domains from AI Overview results

## `country` (type: `string`):

Google search country code

## `language` (type: `string`):

Google search language code

## `min_citations` (type: `integer`):

Minimum number of times a domain must be cited to be included in results

## `max_results` (type: `integer`):

Maximum number of unique domains to return (sorted by citation count)

## Actor input object example

```json
{
  "prompts": [
    "best AI chips for training large language models",
    "leading companies in generative AI infrastructure",
    "top SEO tools for link building in 2026"
  ],
  "country": "US",
  "language": "en",
  "min_citations": 1,
  "max_results": 100
}
```

# Actor output Schema

## `leads` (type: `string`):

Deduped lead table of domains cited in Google AI Overview

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "prompts": [
        "best AI chips for training large language models",
        "leading companies in generative AI infrastructure",
        "top SEO tools for link building in 2026"
    ],
    "country": "US",
    "language": "en",
    "min_citations": 1,
    "max_results": 100
};

// Run the Actor and wait for it to finish
const run = await client.actor("nextgen.api/spark-agent-commerce-ai-citation-lead-extractor").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "prompts": [
        "best AI chips for training large language models",
        "leading companies in generative AI infrastructure",
        "top SEO tools for link building in 2026",
    ],
    "country": "US",
    "language": "en",
    "min_citations": 1,
    "max_results": 100,
}

# Run the Actor and wait for it to finish
run = client.actor("nextgen.api/spark-agent-commerce-ai-citation-lead-extractor").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "prompts": [
    "best AI chips for training large language models",
    "leading companies in generative AI infrastructure",
    "top SEO tools for link building in 2026"
  ],
  "country": "US",
  "language": "en",
  "min_citations": 1,
  "max_results": 100
}' |
apify call nextgen.api/spark-agent-commerce-ai-citation-lead-extractor --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,nextgen.api/spark-agent-commerce-ai-citation-lead-extractor"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/FSp7hRStIBIr62nAe/builds/QqZHfAKZd4SLDPGBq/openapi.json