# LLM Brand Visibility – ChatGPT, Gemini, Claude (`publicrows/llm-brand-visibility`) Actor

Ask ChatGPT, Gemini, Claude and Perplexity your buyers' questions: per prompt and engine, is your brand named, which competitor is, which pages are cited and retrieved, is your domain among them. Live answers with web search, licensed via DataForSEO. $0.08 per check, first 4 free.

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

## Pricing

from $56.00 / 1,000 prompt checked on one engines

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

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

## LLM Brand Visibility – ChatGPT, Gemini, Claude

Ask ChatGPT, Gemini, Claude and Perplexity your buyers' questions: per prompt and engine, is your brand named, which competitor is, which pages are cited and retrieved, is your domain among them. Live answers with web search, licensed via DataForSEO. $0.08 per check, first 4 free.

### Who this is for

Brands and agencies measuring generative-engine visibility (GEO), content teams deciding which pages the assistants trust for a topic, and analysts who want a weekly share-of-voice across the four assistants without paying for a dashboard.

### Sample output

```json
{
  "prompt": "What are the best running shoes for flat feet?",
  "engine": "chatgpt",
  "model": "gpt-4o-mini-2024-07-18",
  "web_search_used": true,
  "brand_in_answer": true,
  "brand_first_match": "Brooks",
  "competitor_in_answer": true,
  "competitor_first_match": "ASICS",
  "citations_count": 9,
  "cited_domains": "[\"bmcsports.ie\",\"theflatfeet.com\",\"paceandpavement.com\",\"shopcgx.com\",\"support.runna.com\",\"paragonsports.com\",\"runrepeat.com\",\"sneakersquad.nl\",\"gearscouted.com\"]",
  "cited_urls": "[\"https://www.bmcsports.ie/product-category/brooks/adrenaline-running-shoes/?utm_source=openai\",\"https://www.theflatfeet.com/?utm_source=openai\",\"https://paceandpavement.com/shoes/best-running-shoes-for-flat-feet?utm_source=openai\",\"https://shopcgx.com/products/1147851-msf-w-arahi-7-midnight-seafoam?utm_source=openai\",\"https://support.runna.com/en/articles/15690288-best-running-shoes-for-flat-feet?utm_source=openai\",\"https://paragonsports.com/products/17_1106844_3?utm_source=openai\",\"https://www.runrepeat.com/guides/best-flat-feet-running-shoes?utm_source=openai\",\"https://www.sneakersquad.nl/new-balance/860/new-balance-fresh-foam-x-860v15-m86039g/?utm_source=openai\",\"https://www.gearscouted.com/running/best-stability-running-shoes-for-flat-feet?utm_source=openai\"]",
  "target_cited": false,
  "target_cited_url": null,
  "retrieved_domains": "[\"runrepeat.com\",\"michiganfootdoctors.com\",\"shoestation.com\",\"support.runna.com\",\"runna.com\",\"theflatfeet.com\",\"paceandpavement.com\",\"fleetfeet.com\",\"gearscouted.com\",\"today.com\",\"achillesfootandankle.com\",\"bmcsports.ie\",\"shopcgx.com\",\"paragonsports.com\",\"sneakersquad.nl\"]",
  "retrieved_count": 16,
  "search_queries_used": "[\"What are the best running shoes for flat feet?\"]",
  "country": "US",
  "checked_at": "2026-11-15T13:37:21.000Z",
  "row_key": "What are the best running shoes for flat feet?|chatgpt|gpt-4o-mini-2024-07-18",
  "source_url": "https://dataforseo.com/apis/ai-optimization-api"
}
```

### What you get

One row per keyword. Every row also carries `_source` (attribution) and the recipe version.

| Field | Type |
| --- | --- |
| `prompt` | string, always present |
| `engine` | string, always present |
| `model` | string, always present |
| `web_search_used` | boolean |
| `brand_in_answer` | boolean |
| `brand_first_match` | string |
| `competitor_in_answer` | boolean |
| `competitor_first_match` | string |
| `citations_count` | number |
| `cited_domains` | string |
| `cited_urls` | string |
| `target_cited` | boolean |
| `target_cited_url` | string |
| `retrieved_domains` | string |
| `retrieved_count` | number |
| `search_queries_used` | string |
| `country` | string |
| `checked_at` | datetime |
| `row_key` | string, always present |
| `source_url` | string |

Every row is one live answer from one assistant to one of your prompts, bought through the DataForSEO AI Optimization API with web search on (ChatGPT gpt-4o-mini and Claude claude-haiku-4-5 with search forced, Gemini gemini-2.5-flash with Google grounding, Perplexity sonar). The actor keeps facts about the answer and never stores or republishes the generated text.

`brand_in_answer` and `competitor_in_answer` match your terms as whole words, case-insensitive; `brand_first_match` and `competitor_first_match` show which term matched first. `cited_domains` and `cited_urls` are the sources the assistant linked in its answer, `retrieved_domains` the pages it read while searching (not returned by Gemini), and `search_queries_used` the sub-queries it ran. `target_cited` is true when a cited page sits on your domain or a subdomain; for Gemini, which returns redirect links, the domain shown in the citation is used.

Answers vary from run to run, as they do for real users, so measure trends with a weekly schedule rather than a single run: 20 prompts × 4 engines once a week is 80 rows, $6.40 a week. Each check costs $0.08 and the first 4 rows of every run are free, so one prompt across all four assistants costs nothing to try.

Bring your own DataForSEO credentials in the two optional inputs if you prefer the supplier charge on your own account; the row price here stays the same either way.

### Pricing

Pay per keyword: $0.08 each ($80.00 per 1,000). The first 4 rows of every run are free, so a test costs nothing.

### How to run

1. Keep the defaults for the standard sample, or set the inputs (listed last, below).
2. Run. Results land in the dataset as JSON, CSV or Excel.
3. From code or an agent: call it through the API, or as an MCP tool via mcp.apify.com.

### Source and fair use

Data: LLM answers through the DataForSEO AI Optimization API, licensed. The data is bought from the supplier under its API terms on every run; nothing is scraped from any website. Rows are facts about keywords, and no personal data of individuals is included.

### FAQ

**How fresh is the data?** Each run fetches live from the source.
**Can I get more fields?** Open an issue naming the field and where it appears at the source.
**Something broke?** Open an issue. Issues are answered within 12 hours.
**Found it useful?** A short review on this page helps other people find it, and tells us what to improve.

### Inputs

- `prompts`: One prompt per line, up to 500 characters each, written the way a buyer would ask an assistant ("best crm for a small agency", "is X worth it"). Each prompt is asked once on every engine you switch on.
- `brandTerms`: Your brand and product names, comma-separated. Matched as whole words, case-insensitive, in the answer text.
- `competitorTerms`: Competitor names, comma-separated. The row says whether any of them is named and which one came first.
- `targetDomain`: Your domain, e.g. example.com. The row says whether a page on it (or a subdomain) is cited by the answer.
- `country`: Country for the assistants' web search (ChatGPT, Claude, Perplexity); Gemini has no country setting.
- `includeChatGPT`: Ask ChatGPT (gpt-4o-mini with web search forced on).
- `includeGemini`: Ask Gemini (gemini-2.5-flash with Google grounding).
- `includeClaude`: Ask Claude (claude-haiku-4-5 with web search forced on).
- `includePerplexity`: Ask Perplexity (sonar, always web-grounded).
- `sandbox`: Use the supplier's test environment: same row structure, dummy data, no supplier charge. For wiring tests only.
- `dfsLogin`: Optional: your own DataForSEO API login (the account e-mail). Leave empty to use ours.
- `dfsPassword`: Optional: your own DataForSEO API password. Leave empty to use ours.
- `maxItems`: Stop after this many rows.

# Actor input Schema

## `prompts` (type: `string`):

One prompt per line, up to 500 characters each, written the way a buyer would ask an assistant ("best crm for a small agency", "is X worth it"). Each prompt is asked once on every engine you switch on.

## `brandTerms` (type: `string`):

Your brand and product names, comma-separated. Matched as whole words, case-insensitive, in the answer text.

## `competitorTerms` (type: `string`):

Competitor names, comma-separated. The row says whether any of them is named and which one came first.

## `targetDomain` (type: `string`):

Your domain, e.g. example.com. The row says whether a page on it (or a subdomain) is cited by the answer.

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

Country for the assistants' web search (ChatGPT, Claude, Perplexity); Gemini has no country setting.

## `includeChatGPT` (type: `boolean`):

Ask ChatGPT (gpt-4o-mini with web search forced on).

## `includeGemini` (type: `boolean`):

Ask Gemini (gemini-2.5-flash with Google grounding).

## `includeClaude` (type: `boolean`):

Ask Claude (claude-haiku-4-5 with web search forced on).

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

Ask Perplexity (sonar, always web-grounded).

## `sandbox` (type: `boolean`):

Use the supplier's test environment: same row structure, dummy data, no supplier charge. For wiring tests only.

## `dfsLogin` (type: `string`):

Optional: your own DataForSEO API login (the account e-mail). Leave empty to use ours.

## `dfsPassword` (type: `string`):

Optional: your own DataForSEO API password. Leave empty to use ours.

## `maxItems` (type: `integer`):

Stop after this many rows.

## Actor input object example

```json
{
  "prompts": "What are the best running shoes for flat feet?",
  "brandTerms": "Brooks, Adrenaline",
  "competitorTerms": "Asics, Nike, Hoka, Saucony, New Balance",
  "targetDomain": "brooksrunning.com",
  "country": "US",
  "includeChatGPT": true,
  "includeGemini": true,
  "includeClaude": true,
  "includePerplexity": true,
  "sandbox": false,
  "maxItems": 4000
}
```

# Actor output Schema

## `rows` (type: `string`):

Dataset items, one per keyword (prompt, engine, model, web_search_used, brand_in_answer, brand_first_match, competitor_in_answer, competitor_first_match, citations_count, cited_domains, cited_urls, target_cited, target_cited_url, retrieved_domains, retrieved_count, search_queries_used, country, checked_at, row_key, source_url). Append ?format=csv or ?format=xlsx for other formats.

## `runSummary` (type: `string`):

Pages fetched, response classes, cost estimate and the quality-gate checks for this run.

# 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": "What are the best running shoes for flat feet?",
    "brandTerms": "Brooks, Adrenaline",
    "competitorTerms": "Asics, Nike, Hoka, Saucony, New Balance",
    "targetDomain": "brooksrunning.com",
    "country": "US",
    "maxItems": 4000
};

// Run the Actor and wait for it to finish
const run = await client.actor("publicrows/llm-brand-visibility").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": "What are the best running shoes for flat feet?",
    "brandTerms": "Brooks, Adrenaline",
    "competitorTerms": "Asics, Nike, Hoka, Saucony, New Balance",
    "targetDomain": "brooksrunning.com",
    "country": "US",
    "maxItems": 4000,
}

# Run the Actor and wait for it to finish
run = client.actor("publicrows/llm-brand-visibility").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": "What are the best running shoes for flat feet?",
  "brandTerms": "Brooks, Adrenaline",
  "competitorTerms": "Asics, Nike, Hoka, Saucony, New Balance",
  "targetDomain": "brooksrunning.com",
  "country": "US",
  "maxItems": 4000
}' |
apify call publicrows/llm-brand-visibility --silent --output-dataset

```

## MCP server setup

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

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/Aw3EpEtdHbYyC7njt/builds/TmLSQCPa1OG1DPKAH/openapi.json
