LLM Brand Visibility Tracker — Are You Cited by ChatGPT, Perplexity & Gemini?

When a buyer asks an AI assistant "what's the best CRM software?", does it name your brand — or your competitors instead? This Actor runs your exact question against real AI models with live web search and reports whether your brand was mentioned, how high it ranked among the names given, and who got recommended in your place. Billing is per query × model row, not per query — see Pricing below before you set a budget.

What you get

• For every query × model pair: mentioned (yes/no), position (how early among the brands the model named), and competitorsCited (who it recommended instead).
• A readable snippet of the model's actual answer, plus promptTokens / completionTokens so you can reconcile against your own LLM bill.
• Billed per query × model row, not per query. 10 queries checked against 2 models is 20 billed rows, not 10 — see Pricing for the exact math.
• Works out of the box — no API key needed. LLM access is built in and covered by the per-row price. Grounded (real web-search) engines: perplexity/sonar, openai/gpt-4o-mini:online, google/gemini-2.5-flash:online. Prefer your own OpenRouter key? Pass it and the tokens bill to your account instead.
• Any language — set lang, the model answers natively.
• Runs on Apify: schedule it, monitor it, call it from the API or the MCP server, export to JSON, CSV or Excel, or push results straight into your own pipeline.

How to run it

1. Click Try for free — no card needed on the free plan.
2. Paste your brand into Brand and your questions into Queries. That's it — no API key needed. (Optionally pick other model IDs in Models, or add your own OpenRouter key to pay for tokens directly.)
3. Press Start. Results appear in the dataset, one row per query × model pair — read them in the UI, pull them from the API, or push them onward with a webhook.

Pricing

Pay-per-event: $0.005 per run start + $0.05 per result row. No monthly seat.

Each result row is one query × model pair, not one query — every model you add multiplies the bill. 10 queries checked against 2 models is 20 billed rows, not 10: 20 × $0.05 + $0.005 start = $1.005 (about $1.01). 100 rows cost about $5.01; 1,000 rows about $50.01.

The per-row price includes the LLM call — by default the Actor runs on built-in model access and you pay nothing beyond the row price. If you pass your own openrouterApiKey, the LLM tokens bill to your OpenRouter account instead (at OpenRouter's own price, nothing marked up), and the Actor's row price stays the same.

A row that fails — a bad response from the model, a timeout, an empty answer — is still written to the dataset with the reason, and it is not charged.

Input

Field	Required	What it does
brand	yes	The brand, product or company to track.
queries	yes	The questions a real buyer would ask (e.g. "best CRM software"). Up to 20.
models	no	OpenRouter model IDs, grounded (web-search) ones: perplexity/sonar, openai/gpt-4o-mini:online, google/gemini-2.5-flash:online. Up to 5. Default perplexity/sonar.
lang	no	Answer language (e.g. en, ru, tr). Default en.
openrouterApiKey	no	Optional. Leave empty to use the built-in LLM access (included in the row price). Pass your own OpenRouter key to have tokens billed to your account instead.
maxConcurrency	no	Parallel LLM calls, 1–10 (default 3).

Every query is checked against every model. With the limits above, the most a single run can produce is 20 queries × 5 models = 100 billed rows.

{
    "brand": "Notion",
    "queries": [
        "best note-taking app",
        "best project management tool for startups"
    ],
    "models": [
        "perplexity/sonar"
    ]
}

Output

One row per query × model pair. This is a real row from a real run:

{
    "brand": "Zzqfake Nonexistent Xyz Corp",
    "query": "best CRM software",
    "model": "perplexity/sonar",
    "lang": "en",
    "found": true,
    "mentioned": false,
    "position": null,
    "competitorsCited": [
        "Salesforce",
        "HubSpot CRM",
        "Zoho CRM",
        "Pipedrive",
        "Microsoft Dynamics 365"
    ],
    "snippet": "The **best CRM software** depends on your business size and needs, but the most broadly recommended options are **Salesforce**, **HubSpot CRM**, **Zoho CRM**, **Pipedrive**, and **Microsoft Dynamics 365**. If you want the safest default choice for most teams, **HubSpot CRM** is o",
    "promptTokens": 96,
    "completionTokens": 234,
    "summary": "perplexity/sonar on \"best CRM software\": Zzqfake Nonexistent Xyz Corp NOT mentioned; competitors: Salesforce, HubSpot CRM, Zoho CRM, Pipedrive, Microsoft Dynamics 365.",
    "checkedAt": "2026-07-26T13:27:30.617Z"
}

Field	What it means
mentioned	Did the model name the brand in its answer
position	How early among the named brands (1 = first); null if not mentioned
competitorsCited	Other brands/products the model named instead
snippet	The first ~280 characters of the model's actual answer
promptTokens / completionTokens	Token usage for this call, straight from OpenRouter's own response — reconcile against your OpenRouter invoice
found	false means the call itself failed (bad response, timeout, empty answer); the row explains why and is not billed

Related tools

Related tools for adjacent workflows in AI and search visibility.

Actor	What it does
AI Overview Citation Tracker	Pair it in the AI and search visibility workflow: For each query that matters, see which sources and domains AI assistants cite in their answer — grounded...
AI Answer Change Alert	Pair it in the AI and search visibility workflow: Track whether an AI assistant's answer to a query you care about changed since last time — new sources...
AI Crawler Access Checker	Pair it in the AI and search visibility workflow: Check which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended & more) can access your website
Domain Health Checker	Pair it in the AI and search visibility workflow: Bulk-audit domains: DNS records, SSL certificate expiry, SPF & DMARC email authentication
Social Preview Checker	Pair it in the AI and search visibility workflow: See exactly how your links look when shared on Telegram, WhatsApp, X, LinkedIn, Slack, Facebook & Discord

FAQ

Do I need an API key? No — it works out of the box, LLM access is built in and covered by the row price. Passing your own OpenRouter key is optional: do it if you want the tokens billed to your account at OpenRouter's own price, with your own rate limits.

Which languages? Any — set lang (e.g. ru, tr). Grounded models answer natively in that language.

Can an agent call it? Yes — standard Apify Actor, callable from the Apify API, the SDK, or the Apify MCP server.

What this is NOT. It does not audit your SEO, crawl your site, or guarantee future rankings in AI answers. It answers one question per query × model pair — did the model name your brand right now, in a live grounded answer — and shows its work.

Found a wrong result, or need a check we don't run? Open an issue on this Actor's page.

---

Built by zinin. Questions? Telegram @timzinin.