# LLM Brand Visibility and Citation Tracker (`dltik/llm-visibility-tracker`) Actor

Track how your brand appears in LLM answers (ChatGPT, Perplexity, Gemini, optional Claude): brand mentions & aliases, response rank/position, Share of Voice vs competitors, citation signals, sentiment, and a 0-100 visibility score. One run returns per-prompt evidence plus a structured summary.

- **URL**: https://apify.com/dltik/llm-visibility-tracker.md
- **Developed by:** [Walid](https://apify.com/dltik) (community)
- **Categories:** AI, SEO tools, Marketing
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.00005 / actor start

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/platform/actors/running/actors-in-store#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

## LLM Brand Visibility and Citation Tracker — ChatGPT, Perplexity, Gemini & Claude

> Track how your brand appears inside **LLM answers** — mentions, rank, **Share of Voice**, **citations**, competitors and sentiment across **ChatGPT, Perplexity, Gemini and Claude** — in one run. Get a **0-100 visibility score** plus **per-prompt evidence**. **$0.07 per check** (1 check = 1 prompt × 1 LLM).

⭐ **Bookmark this LLM Visibility Tracker** to keep it on top of your Apify dashboard — Apify ranks actors by bookmarks.

### What is the LLM Brand Visibility and Citation Tracker?

The **LLM Brand Visibility and Citation Tracker** measures how large language models talk about your brand. For each prompt and model it detects **brand mentions** (including aliases), estimates **rank and position** within ordered answers, measures **Share of Voice** versus your competitors, captures **citation signals** and source URLs where your domain appears, scores **sentiment**, and rolls everything up into an overall **visibility score (0-100)**. It also surfaces **content gaps** (prompts where competitors appear but you don't) with actionable recommendations.

It is the answer-engine (AEO) / generative-engine (GEO) equivalent of rank tracking: instead of "where do I rank on Google", it tells you "how do ChatGPT, Perplexity, Gemini and Claude recommend, rank and cite my brand".

### Use cases

- **AEO / GEO monitoring** — track your brand's presence inside LLM answers over time.
- **Share of Voice** — compare your brand against named competitors across models.
- **Citation analysis** — find which prompts make an LLM cite your website (or a competitor's).
- **Content gaps** — see the exact questions where rivals appear and you don't, with editorial recommendations.
- **Sentiment** — how positively/negatively models describe your brand.
- **Scheduled reporting** — run weekly and POST the summary to your own pipeline via `webhookUrl`.
- **Agencies** — repeatable client visibility reports across ChatGPT, Perplexity, Gemini and Claude.

### Input

Give a `brand` (required) and either `keywords` (prompts are auto-generated) or `customPrompts` (your exact questions). Add `competitors` for Share of Voice, `domain` for citation detection, and pick a `mode` (quick / standard / deep) to control depth.

```json
{
  "brand": "Apify",
  "domain": "apify.com",
  "aliases": ["Apify Technologies"],
  "competitors": ["Bright Data", "Zyte", "ScrapingBee"],
  "category": "web scraping",
  "keywords": ["web scraping tool", "data extraction API"],
  "mode": "standard",
  "llms": ["openai/gpt-4o-mini", "anthropic/claude-haiku-4.5", "google/gemini-2.0-flash-001"],
  "includePerplexity": true
}
```

> **Free dry-run:** set `"demoMode": true` to validate your setup without calling any LLM and without being charged.

### Output

One `llm_visibility_report` summary record (visibility score, mention rate, citation rate, platform coverage, Share of Voice, top gaps, recommendations), followed by one `visibility_check` evidence record per prompt × LLM (mention, citation, position, sentiment, competitors detected, answer excerpt). Optionally POSTed to your `webhookUrl`.

### Pricing

**Pay per event: $0.07 per visibility check.** One check = one prompt sent to one LLM. A `standard` run of 3 keywords × 5 prompts × 3 LLMs = 45 checks. Use `mode` and `maxPrompts` to control spend.

### FAQ

**Which models are supported?** ChatGPT (GPT-4o family), Claude, Gemini via OpenRouter, plus Perplexity for live-search citations.

**How is this different from a single-metric GEO actor?** It consolidates mentions, rank, Share of Voice, citations, competitors and sentiment into one run and one output — no need to chain several actors.

**Can I schedule it?** Yes. Run it on an Apify schedule and set `webhookUrl` to receive each summary in your own system.

# Actor input Schema

## `brand` (type: `string`):

The brand, product, company or tool name to track in LLM answers (e.g. 'Notion', 'Ahrefs').

## `domain` (type: `string`):

Optional but recommended. The brand's primary domain (e.g. 'notion.so', 'ahrefs.com'). Used to detect citations of your site.

## `aliases` (type: `array`):

Optional. Other names the brand is known by (e.g. \['Notion HQ', 'Notion Labs']). Improves mention detection.

## `competitors` (type: `array`):

Optional but high-value. Up to ~10 competitor brand names (e.g. \['Coda', 'ClickUp']). Enables Share of Voice and gap analysis.

## `category` (type: `string`):

Optional. The category the brand competes in (e.g. 'project management', 'web scraping'). Improves auto-generated prompts.

## `keywords` (type: `array`):

Topics to test. Prompts are auto-generated per keyword (e.g. \['web scraping tool', 'data extraction API']). Provide this OR customPrompts.

## `customPrompts` (type: `array`):

Optional. Exact prompts to send to each LLM, phrased the way your customers ask. Sent as-is (no auto-generation). Provide this OR keywords.

## `mode` (type: `string`):

Depth preset controlling prompts generated per keyword: 'quick' (3), 'standard' (5), 'deep' (10). More prompts = more thorough and more billable checks.

## `llms` (type: `array`):

The LLMs to query via OpenRouter. Defaults to GPT-4o-mini, Claude Haiku and Gemini Flash.

## `includePerplexity` (type: `boolean`):

Also query Perplexity (adds a live-search engine with native citations) when a Perplexity key is configured.

## `maxPrompts` (type: `integer`):

Optional override. Hard cap on the total number of unique prompts sent (across all keywords), before multiplying by the number of LLMs.

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

Two-letter country context for prompt generation (e.g. 'US', 'FR').

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

Two-letter language for prompts and answers (e.g. 'en', 'fr').

## `webhookUrl` (type: `string`):

Optional HTTPS URL that receives a POST with the full run summary when the run finishes. Useful for scheduled monitoring pipelines.

## `demoMode` (type: `boolean`):

When true, runs a connectivity check without calling any LLM and exits. Nothing is charged. Use it to validate your setup for free.

## Actor input object example

```json
{
  "brand": "Apify",
  "domain": "apify.com",
  "aliases": [],
  "competitors": [],
  "keywords": [
    "web scraping tool",
    "data extraction API"
  ],
  "customPrompts": [],
  "mode": "standard",
  "llms": [
    "openai/gpt-4o-mini",
    "anthropic/claude-haiku-4.5",
    "google/gemini-2.0-flash-001"
  ],
  "includePerplexity": true,
  "country": "US",
  "language": "en",
  "demoMode": false
}
```

# Actor output Schema

## `results` (type: `string`):

GEO Score and full visibility breakdown per LLM and keyword.

# 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 = {
    "brand": "Apify",
    "domain": "apify.com",
    "aliases": [],
    "competitors": [],
    "category": "",
    "keywords": [
        "web scraping tool",
        "data extraction API"
    ],
    "customPrompts": [],
    "llms": [
        "openai/gpt-4o-mini",
        "anthropic/claude-haiku-4.5",
        "google/gemini-2.0-flash-001"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("dltik/llm-visibility-tracker").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 = {
    "brand": "Apify",
    "domain": "apify.com",
    "aliases": [],
    "competitors": [],
    "category": "",
    "keywords": [
        "web scraping tool",
        "data extraction API",
    ],
    "customPrompts": [],
    "llms": [
        "openai/gpt-4o-mini",
        "anthropic/claude-haiku-4.5",
        "google/gemini-2.0-flash-001",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("dltik/llm-visibility-tracker").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 '{
  "brand": "Apify",
  "domain": "apify.com",
  "aliases": [],
  "competitors": [],
  "category": "",
  "keywords": [
    "web scraping tool",
    "data extraction API"
  ],
  "customPrompts": [],
  "llms": [
    "openai/gpt-4o-mini",
    "anthropic/claude-haiku-4.5",
    "google/gemini-2.0-flash-001"
  ]
}' |
apify call dltik/llm-visibility-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,dltik/llm-visibility-tracker"
        }
    }
}

```

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/HOj60L9gxKVn3exsx/builds/CAwqqXe0hChO60q3M/openapi.json