AI Brand Mention Tracker - Mentions and Citations Lookup

AI brand monitoring from indexed LLM answers at scale. Enter domain targets or keyword targets with market and platform settings. The Actor turns that input into structured mention rows automatically.

It returns structured JSON with question, answer, platform, sources, search results, and index metadata on every row.

Designed for SEO teams, brand managers, and developers, the Actor returns one filterable row per mention. Index lookup only. No live prompts.

Launch price: 30% OFF until 8 November 2026

Now $2.75 / 1,000 mention rows ($0.00275 each). Regular rate is $4.00 / 1,000 from 8 November 2026.

A default run with 100 mentions costs about $0.27505 plus actor start.

One Row per Mention

Reports? Not here.

Enter domain or keyword targets with location and language. Each dataset row is one mention with question text, answer text, sources, and timestamps. Filter and export mentions in the first minute.

Use Cases

• Look up brand mentions for a domain or keyword target
• Read citations in indexed LLM answers with full question and answer text
• Export mention rows to spreadsheets or data pipelines
• Compare ChatGPT and Google index mentions for United States English markets
• Run recurring mention lookups for up to 10 targets per run

Index

• Release Notes
• AI Brand Monitoring by Keyword
• Features
• Use Cases
• Pricing
• Input
• Input Example (Domain targets)
• Input Example (Keyword targets)
• API and MCP usage
• Output Structure
• Output Example

Release Notes

v0.0 - Initial public release

• One row per mention: Each dataset row is one mention with question, answer, platform, and sources
• Domain and keyword targets: Up to 10 combined targets per run with market and platform filters
• Linear per-row pricing: Pay per mention row written with resultCharged true

AI Brand Monitoring by Keyword

Pass keywords instead of domains when your target is a brand name or term. The Actor sends keyword objects to the mention index. Default match type is word_match. Keyword-only runs accept searchScope values any, question, answer, brand_entities, and fan_out_queries.

Each mention row written costs mention-row at the launch rate ($2.75 / 1,000 mention rows, 30% off).

Features

📄 One row per mention: Primary output is a flat mention row, not a nested report.

🔍 Domain and keyword targets: Combine up to 10 domain and keyword entries in one run.

🌐 ChatGPT and Google platforms: Query both indexes where available, or restrict to one platform.

📎 Sources on each row: sources and search_results stay on the same mention row.

🔄 Include or exclude filter: Keep mentions that hit your targets, or rows that miss them.

📊 Index total count: Every row carries index_total_count from the index, even when caps stop early.

🛑 Page and result caps: maxResults and maxPages stop the search before the full index is fetched.

📋 Metadata on every row: _metadata.resultCharged shows billing status. Diagnostic rows use _metadata.error.

Pricing

Launch pricing: 30% off (until 2026-11-08)

Cost item	Rate
Mention row (1 mention)	$0.00275
Per 1,000 mention rows	$2.75 / 1,000 mentions
Actor start	$0.00005 (infrequent)
Apify platform compute (RAM/time)	Billed by Apify platform pricing

Regular pricing (from 2026-11-08)

Cost item	Rate
Mention row (1 mention)	$0.004
Per 1,000 mention rows	$4.00 / 1,000 mentions
Actor start	$0.00005 (infrequent)
Apify platform compute (RAM/time)	Billed by Apify platform pricing

Launch is 30% off: ~$0.00275 per mention. Default run with 100 mentions costs about $0.27505 including actor start.

You pay only for mention rows written with resultCharged true. Diagnostic rows and deduplicated skips are not charged.

Free plan limit

Runs from Apify free plan accounts are limited to 100 mention rows and 1 index page per run. The run finishes normally at that point and keeps every result already written.

Cost Examples

Based on the launch prices above (30% off).

Scenario A: Default run (100 mentions)

• Actor start: $0.00005
• 100 mentions: $0.275
• Total: ~$0.27505

Scenario B: Full index page (1,000 mentions)

• Actor start: $0.00005
• 1,000 mentions: $2.75
• Total: ~$2.75005

Scenario C: Maximum run (5,000 mentions)

• Actor start: $0.00005
• 5,000 mentions: $13.75
• Total: ~$13.75005

Input

The Actor accepts the following input parameters (see the Input tab in the Apify Console for the full, interactive schema):

Parameter	Type	Required	Default	Description
domains	array of string	when combined with keywords	[]	Domains to look up in the mention index. One hostname per entry, not a full URL. Example: apple.com. After cleanup the two lists together must have 1-10 targets.
keywords	array of string	when combined with domains	[]	Brand or term targets in the mention index. One term per entry. After cleanup the two lists together must have 1-10 targets.
location	string	no	United States	Geographic market of the indexed answers. Example: United States. Must match a known market name. A typo fails.
language	string	no	en	Language code of the indexed answers. Example: en. Must be valid for the chosen location. Names such as English fail.
platform	string (enum)	no	both	Which index platform to query. Values: both, chat_gpt, google. ChatGPT index is available for United States and English only.
searchFilter	string (enum)	no	include	include keeps mentions that hit the targets. exclude keeps mentions that miss the targets.
searchScope	string (enum)	no	any	Where the target must appear. Domain-only runs accept any, sources, search_results. Keyword-only runs accept any, question, answer, brand_entities, fan_out_queries. Mixed targets accept any only.
includeSubdomains	boolean	no	false	When true, the lookup includes subdomains of domain targets. Ignored when the run has no domain target.
matchType	string (enum)	no	word_match	How keywords match. word_match treats the keyword as a whole word. partial_match treats it as a substring. Ignored when the run has no keyword.
maxResults	integer	no	100	Maximum mention rows to write. Range 1-5000. Apify Free plan: 100 mention rows per run.
maxPages	integer	no	5	Maximum index pages to fetch. Range 1-10. Stops the search even if fewer mention rows exist. Apify Free plan: 1 page.

Input Example (Domain targets)

{
  "domains": ["apple.com"],
  "location": "United States",
  "language": "en",
  "platform": "both",
  "maxResults": 100
}

Input Example (Keyword targets)

{
  "keywords": ["Apple"],
  "location": "United States",
  "language": "en",
  "platform": "both",
  "matchType": "word_match",
  "maxResults": 100
}

API and MCP usage

Runs write one dataset row per mention. Fetch rows from the default dataset after the run succeeds (or use the synchronous endpoint below).

REST (sync, returns dataset items): replace YOUR_USERNAME, YOUR_API_TOKEN, and use the same JSON body as in Input Example.

curl "https://api.apify.com/v2/acts/YOUR_USERNAME~llm-mentions-index/run-sync-get-dataset-items?token=YOUR_API_TOKEN" \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{"domains":["apple.com"],"location":"United States","language":"en","maxResults":100}'

JavaScript (apify-client):

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const input = {
  domains: ['apple.com'],
  location: 'United States',
  language: 'en',
  maxResults: 100,
};
const run = await client.actor('YOUR_USERNAME~llm-mentions-index').call(input);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Apify MCP server (AI agents): configure your MCP client with URL https://mcp.apify.com?tools=YOUR_USERNAME~llm-mentions-index (you can combine multiple tools per Apify MCP docs). Pass the API token via your client (for example an Authorization: Bearer ... header), not inside the Actor input JSON.

Output Structure

The Actor writes one dataset row per mention. The table below lists every field.

The Output tab has two tables. Overview shows question, platform, model, sources, and timestamps. Mentions adds the full answer plus citation arrays. JSON export contains every field.

Field	Type	Description	Example Value
question	string	Indexed user question for this mention	"What is Apple?"
answer	string	Indexed model answer text	"Apple is a technology company."
platform	string	Index platform for this mention	"chat_gpt"
model_name	string | null	Model name when present	"gpt-4o"
location_code	number | null	Numeric location code from the index	2840
language_code	string	Language code of the mention	"en"
first_response_at	string | null	First indexed response timestamp	"2026-01-15 12:00:00 +00:00"
last_response_at	string | null	Last indexed response timestamp	"2026-08-01 12:00:00 +00:00"
sources	array	Source objects with name, title, domain, and url	[{"source_name":"Apple","title":"Apple","domain":"apple.com","url":"https://www.apple.com/"}]
search_results	array	Search result objects linked to the mention	[{"title":"Apple","domain":"apple.com","url":"https://www.apple.com/"}]
domains	array of string	Echo of cleaned domain targets from input	["apple.com"]
keywords	array of string	Echo of cleaned keyword targets from input	[]
location	string	Echo of input location name	"United States"
language	string	Echo of input language code	"en"
platformRequested	string	Echo of input platform enum	"both"
index_total_count	number	Total mentions in the index for this query	40723
ai_search_volume	number | null	Raw index field, not a volume product	1200
monthly_searches	object | null	Raw monthly object with YYYY-MM keys	{"2026-08": 1200}
fan_out_queries	array of string	Related queries on the mention	["apple iphone"]
brand_entities	array	Brand entities with title and category	[{"title":"Apple","category":"brand"}]
_metadata.resultCharged	boolean	Whether this row was charged	true
_metadata.error	string | null	Present on failure or empty diagnostic rows	(varies)
_metadata.errorContext	string | null	Extra error context when error is set	(varies)

Multiple targets in one run form one combined set, not separate brand reports. ai_search_volume and monthly_searches are raw columns on each row, not a separate volume export. fan_out_queries and brand_entities stay on the same mention row.

Output Example

{
  "question": "What is Apple?",
  "answer": "Apple is a technology company known for iPhone, Mac, and services.",
  "platform": "chat_gpt",
  "model_name": "gpt-4o",
  "location_code": 2840,
  "language_code": "en",
  "first_response_at": "2026-01-15 12:00:00 +00:00",
  "last_response_at": "2026-08-01 12:00:00 +00:00",
  "sources": [
    {
      "source_name": "Apple",
      "title": "Apple",
      "domain": "apple.com",
      "url": "https://www.apple.com/"
    }
  ],
  "search_results": [],
  "domains": ["apple.com"],
  "keywords": [],
  "location": "United States",
  "language": "en",
  "platformRequested": "both",
  "index_total_count": 40723,
  "ai_search_volume": null,
  "monthly_searches": null,
  "fan_out_queries": [],
  "brand_entities": [],
  "_metadata": {
    "resultCharged": true,
    "error": null,
    "errorContext": null
  }
}