# AI Visibility Tracker (ChatGPT, Perplexity, Gemini) (`azet-io/ai-visibility-tracker`) Actor

Track whether ChatGPT, Perplexity and Gemini mention your brand and cite your domain for the questions your customers ask. Uses official APIs with your own keys.

- **URL**: https://apify.com/azet-io/ai-visibility-tracker.md
- **Developed by:** [AZET](https://apify.com/azet-io) (community)
- **Categories:** SEO tools, AI
- **Stats:** 2 total users, 1 monthly users, 75.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

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

## 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 Visibility Tracker — are ChatGPT, Perplexity and Gemini recommending you?

Ask the AI engines the questions your customers ask, and get one row per question and engine telling you:

- **mentioned** — is your brand named in the answer?
- **cited** — is your domain among the sources the engine cites? (**citationRank** = its position in the source list)
- **competitorsMentioned** — which competitors the answer names instead
- **citations** — every cited source, so you can see who the engine trusts for that question
- **answer** — the answer text (first 4,000 characters)

Run it on a schedule and you have an AI share-of-voice history for your brand (GEO / AEO / LLM SEO tracking).

### How it works

The actor calls each engine's **official API with live web search** — Gemini with Google Search grounding, Perplexity `sonar`, and OpenAI Responses API with web search — using **your own API key**. No scraping, no proxies, no logged-in sessions, so runs are stable and you only pay the engine for what you ask. Add one, two or all three keys; engines without a key are skipped. Keys are secret inputs and are never written to the dataset or log.

Answers from the API can differ from what a logged-in user sees in the consumer app (personalisation, location, model tier). Treat the result as a consistent benchmark over time, not a screenshot of one user's chat.

### Input

```json
{
  "queries": ["best project management tool for small teams", "asana alternatives"],
  "brand": ["Asana"],
  "domain": "asana.com",
  "competitors": ["Trello", "Monday", "ClickUp"],
  "geminiApiKey": "…", "perplexityApiKey": "…", "openaiApiKey": "…"
}
```

Up to 100 questions per run. Any language works — ask in the language your customers use.

### Output (one row per question × engine)

`query, engine (gemini | perplexity | chatgpt), mentioned, cited, citationRank, competitorsMentioned, citations, answer, checkedAt`. If an engine call fails (bad key, quota), the row carries `error` and the run continues.

### Related

- **AI Search Readiness Checker** (azet-io/ai-search-readiness) — can AI crawlers read your site at all?
- **llms.txt Generator** (azet-io/llms-txt-generator) — draft an `/llms.txt` from your sitemap.

### Pricing

Free for now (you pay only your own engine API usage). Pay-per-event pricing is planned; it will be announced on this page before it starts.

Made by AZET (azet.io).

# Actor input Schema

## `queries` (type: `array`):

Questions your customers would ask an AI assistant, one per line (max 100).

## `brand` (type: `array`):

Brand names to look for in the answer text. Matching ignores case.

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

Domain to look for among the cited sources, e.g. example.com (subdomains match).

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

Reported per answer as competitorsMentioned.

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

Your own Google AI Studio key. Gemini is asked with Google Search grounding.

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

Your own Perplexity API key (model: sonar).

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

Your own OpenAI key. ChatGPT is asked through the Responses API with web search.

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

Model id used for Gemini.

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

Model id used for ChatGPT (must support web search).

## Actor input object example

```json
{
  "queries": [
    "best project management tool for small teams"
  ],
  "brand": [
    "Asana"
  ],
  "domain": "asana.com",
  "geminiModel": "gemini-flash-latest",
  "openaiModel": "gpt-4o-mini"
}
```

# Actor output Schema

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

No description

# 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 = {
    "queries": [
        "best project management tool for small teams"
    ],
    "brand": [
        "Asana"
    ],
    "domain": "asana.com"
};

// Run the Actor and wait for it to finish
const run = await client.actor("azet-io/ai-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 = {
    "queries": ["best project management tool for small teams"],
    "brand": ["Asana"],
    "domain": "asana.com",
}

# Run the Actor and wait for it to finish
run = client.actor("azet-io/ai-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 '{
  "queries": [
    "best project management tool for small teams"
  ],
  "brand": [
    "Asana"
  ],
  "domain": "asana.com"
}' |
apify call azet-io/ai-visibility-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,azet-io/ai-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/r43wKEL2HniFakMMg/builds/2HhgPuMMAqedpax0R/openapi.json