# AI Brand Visibility Tracker - ChatGPT, Gemini, Claude (GEO) (`henrycrawl/ai-brand-visibility-tracker`) Actor

Track whether ChatGPT, Gemini, Claude and Perplexity mention your brand vs competitors, at what rank, and which sites they cite. Official APIs with your own keys (BYOK), any language or market. $0.01 per answer analysed.

- **URL**: https://apify.com/henrycrawl/ai-brand-visibility-tracker.md
- **Developed by:** [Henry Crawl](https://apify.com/henrycrawl) (community)
- **Categories:** AI, SEO tools
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 87.5% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $10.00 / 1,000 answer analyseds

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?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## AI Brand Visibility Tracker (GEO) — ChatGPT, Gemini, Claude, Perplexity

Find out **whether AI assistants recommend your brand**: ask the questions your customers ask, to ChatGPT (OpenAI), Gemini, Claude and Perplexity at once, and get back **who is mentioned, in what order, and which websites the AI cites** — for your brand and every competitor.

Built for **GEO / AEO (Generative Engine Optimization)**, SEO agencies, marketers and AI agents that monitor brand presence in AI answers.

### Why this tracker

| | This Actor | Typical AI visibility trackers |
|---|---|---|
| Price | **$0.01 per answer analysed** | $0.05–0.30 per check |
| How answers are obtained | **Official APIs** with web search (OpenAI Responses + web_search, Gemini + Google Search grounding, Claude + web search, Perplexity Sonar) | Often scraping chat UIs (fragile) |
| Your cost for the AI | Paid directly to the provider with **your own API key** (Gemini has a free tier) | Hidden in a high per-check price |
| Several AIs per run | Yes, same prompts, side by side | Often one AI per Actor |
| Statistical | `repeatsPerPrompt` → mention **rate**, not one random sample | Single answer |
| Markets & languages | Prompts in any language + optional market / answer language | Mostly English / US |
| Competitors | Share of voice, rank order, aliases (`Microsoft OneNote|OneNote`) | Often brand only |
| Citations | Cited domains per answer + "was my own site cited?" | Rare |

### Input

```json
{
  "brand": "Notion",
  "brandAliases": ["Notion AI"],
  "brandDomains": ["notion.so", "notion.com"],
  "competitors": ["Obsidian", "Evernote", "Microsoft OneNote|OneNote", "ClickUp"],
  "prompts": [
    "What are the best note-taking apps for students?",
    "Welche Notiz-App ist am besten für Teams?"
  ],
  "repeatsPerPrompt": 3,
  "market": "Germany",
  "geminiApiKey": "…",
  "openaiApiKey": "…"
}
```

Add a key for every AI you want to test; providers without a key are skipped. Keys are stored as secret input and only sent to that provider's official API.

### Output

**One row per answer** (`recordType: "answer"`, charged):

```json
{
  "provider": "gemini",
  "model": "gemini-2.5-flash",
  "prompt": "What are the best note-taking apps for students?",
  "repeat": 1,
  "status": "OK",
  "brandMentioned": true,
  "brandRank": 1,
  "brandMentionCount": 2,
  "brandContext": "… **Notion:** Frequently cited as the best all-in-one app for college students …",
  "brandsInOrder": ["Notion", "OneNote", "GoodNotes", "Obsidian"],
  "competitorsMentioned": ["OneNote", "GoodNotes", "Obsidian"],
  "citedDomains": ["zapier.com", "stjohns.edu", "remnote.com"],
  "brandDomainCited": false,
  "citationCount": 12,
  "answer": "full answer text …",
  "citations": [{ "url": "…", "title": "zapier.com" }]
}
```

**Summary rows** (`recordType: "summary"`, free): one for all providers and one per provider, with `brandMentionRate`, `brandAvgRank`, `brandFirstMentionRate`, `brandDomainCitedRate`, `shareOfVoice` and `mentionRate` per brand, `topCitedDomains`.

**Error rows** (free): `AUTH_ERROR` (key rejected — that provider is skipped for the rest of the run), `RATE_LIMITED`, `BAD_REQUEST`, `EMPTY_ANSWER`, `PROVIDER_ERROR`, `NETWORK_ERROR`.

### Pricing

**$0.01 per answer analysed** (+ Apify's tiny start fee). Errors and summary rows are free.
The AI providers bill your own API key for the model call (Gemini Flash with grounding has a free tier; GPT-4.1-mini, Claude Haiku and Sonar cost fractions of a cent to a few cents per answer).

Example: 10 prompts × 3 repeats × 2 AIs = 60 answers = **$0.60** on Apify.

### Notes

- API answers with web search are close to, but not identical with, what a logged-in user sees in the ChatGPT / Gemini apps (personalisation, memory and A/B tests differ). Use repeats and track trends over time.
- Mentions are matched on whole words (case-insensitive); Japanese / Chinese / Korean / Thai names are matched as substrings. URLs inside the answer don't count as mentions.
- Gemini returns redirect links for sources; the cited domain is taken from the source title Google provides.
- Schedule it weekly with the same prompts to build a GEO visibility trend.

# Actor input Schema

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

Brand name exactly as people write it, e.g. "Notion".

## `brandAliases` (type: `array`):

Other spellings / product names that count as your brand, e.g. \["Notion AI", "Notion.so"].

## `brandDomains` (type: `array`):

Used to check whether the AI cites your own website, e.g. \["notion.so"].

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

Competitor names. Add aliases with |, e.g. "Microsoft OneNote|OneNote".

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

The questions your customers ask AI assistants. Write them in the language of your market for local results.

## `repeatsPerPrompt` (type: `integer`):

AI answers vary. Ask each prompt several times to get a mention RATE instead of a single sample.

## `market` (type: `string`):

Appended as "I am based in <market>." e.g. "Germany", "Vietnam", "Austin, Texas".

## `answerLanguage` (type: `string`):

Appended as "Answer in <language>." e.g. "German". Leave empty to let the prompt language decide.

## `geminiApiKey` (type: `string`):

From Google AI Studio (free tier available). Uses Gemini with Google Search grounding.

## `openaiApiKey` (type: `string`):

Uses the Responses API with the web_search tool (closest to ChatGPT search).

## `anthropicApiKey` (type: `string`):

Uses Claude with the web search tool.

## `perplexityApiKey` (type: `string`):

Uses Perplexity Sonar (search built in).

## `geminiModel` (type: `string`):

Default gemini-2.5-flash.

## `openaiModel` (type: `string`):

Default gpt-4.1-mini.

## `anthropicModel` (type: `string`):

Default claude-opus-5-5. Use claude-haiku-5-5 for a cheaper run.

## `perplexityModel` (type: `string`):

Default sonar.

## `maxConcurrency` (type: `integer`):

Lower it if your API plan has strict rate limits (e.g. Gemini free tier).

## Actor input object example

```json
{
  "brand": "Notion",
  "brandAliases": [],
  "brandDomains": [
    "notion.so",
    "notion.com"
  ],
  "competitors": [
    "Obsidian",
    "Evernote",
    "Microsoft OneNote|OneNote",
    "ClickUp"
  ],
  "prompts": [
    "What are the best note-taking apps for students?",
    "Which project management tool is best for a small startup?"
  ],
  "repeatsPerPrompt": 1,
  "maxConcurrency": 3
}
```

# Actor output Schema

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

Analysed AI answers and summary rows.

## `summary` (type: `string`):

Counts per status for this run (SUMMARY record).

# 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": "Notion",
    "brandDomains": [
        "notion.so",
        "notion.com"
    ],
    "competitors": [
        "Obsidian",
        "Evernote",
        "Microsoft OneNote|OneNote",
        "ClickUp"
    ],
    "prompts": [
        "What are the best note-taking apps for students?",
        "Which project management tool is best for a small startup?"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("henrycrawl/ai-brand-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": "Notion",
    "brandDomains": [
        "notion.so",
        "notion.com",
    ],
    "competitors": [
        "Obsidian",
        "Evernote",
        "Microsoft OneNote|OneNote",
        "ClickUp",
    ],
    "prompts": [
        "What are the best note-taking apps for students?",
        "Which project management tool is best for a small startup?",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("henrycrawl/ai-brand-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": "Notion",
  "brandDomains": [
    "notion.so",
    "notion.com"
  ],
  "competitors": [
    "Obsidian",
    "Evernote",
    "Microsoft OneNote|OneNote",
    "ClickUp"
  ],
  "prompts": [
    "What are the best note-taking apps for students?",
    "Which project management tool is best for a small startup?"
  ]
}' |
apify call henrycrawl/ai-brand-visibility-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,henrycrawl/ai-brand-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/HTOLyOywCqdyRFFBY/builds/lXEM1O1lC4Pdq7Xrz/openapi.json
