Grok Rank Tracker: Brand Visibility, Mentions & Pages Read

Grok Brand Visibility Tracker: Mentions & Pages Read

Watch the 25-second film

Does Grok recommend your brand when your buyers ask? This Actor asks Grok your buyers' questions through xAI's official API with xAI's own web search, and returns every answer, every page it came across, and whether each of your brands is named, with a per-brand mention rate and rank for GEO / AEO tracking.

What Grok doesn't tell you: which of those pages it used. It lists 60 to 90 pages an answer with nothing tying any of them to its words, so we report them as pages read, not as citations, and we don't give Grok a citation share. To see who gets cited, use AI Visibility Tracker with ChatGPT, Perplexity or Claude.

Always the newest model. Each run uses the newest Grok model at that moment (on 12 October 2026: Grok 4.7), so your tracking follows what people actually get. You can pin a model under Advanced.

Try it in a minute: the form is filled in. Press Start and you get the answer, the pages it read, a brand report and a monitoring baseline. One question costs $0.10, plus the AI usage at cost.

Then run it every week. Keep the project name and add a schedule (Actor page, then Schedules). Each run shows the mentions you gained and lost since the last one, per question, and which competitors moved.

What you get

For every question and run:

• The full Grok answer.
• Every page it came across, URL and domain, in pagesRead. citations stays empty unless Grok writes a link into its answer.
• For each brand you track: named or not, and its rank among your brands by first mention. cited is null, because Grok doesn't say.
• The exact model, the country used, the time, and the AI cost of that answer.

The key-value store record SUMMARY gives, per brand: mention rate and average rank, plus the sites it read most (topReadDomains).

Input

{
  "prompts": ["What is the best CRM for a small business?", "best accounting software for freelancers"],
  "brands": ["HubSpot | hubspot.com", "Zoho | zoho.com", "Pipedrive | pipedrive.com"],
  "country": "US",
  "runsPerPrompt": 3
}

• prompts: the questions, one per line, as buyers would type them into Grok.
• brands: a name, a domain, or both as Name | domain.com.
• country: Grok searches as a user in that country (two-letter code).
• runsPerPrompt: answers vary from run to run; use 3 or more for a stable mention rate.
• Advanced: a fixed model (an OpenRouter model id), answer length and concurrency.

Output

One row per question and run:

{
  "prompt": "What is the best CRM for a small business?",
  "engine": "grok",
  "model": "...",
  "run": 1,
  "status": "ok",
  "answer": "...",
  "citations": [],
  "citedDomains": [],
  "pagesRead": [{ "url": "https://...", "domain": "...", "cited": false }],
  "citationsUnknown": true,
  "brands": [{ "brand": "HubSpot", "domain": "hubspot.com", "mentioned": true, "mentionRank": 1, "cited": null, "citedPosition": null }],
  "mentionedBrands": ["HubSpot", "Zoho", "Pipedrive"],
  "aiCostUsd": 0.03,
  "charged": true
}

status is ok (an answer it searched for), zero-cite (an answer without searching, still data) or error (free).

Pricing

• $0.10 per Grok answer analysed, with the pages it read and brand matches. Lower on Apify's Scale and Business plans (Store discounts).
• AI usage is billed to your Apify account by Apify's own OpenRouter gateway at OpenRouter's rates for paying Apify plans: Grok (Grok 4.7) cost $0.15-0.23 (it reads 60 or more pages per answer) per answer on 12 October 2026.
• Failed calls are free. Your spending limit for the run is respected.

All engines in one run

To ask ChatGPT, Perplexity, Gemini, Claude, Grok and Google's AI Overview the same questions in one run, with one summary across them, use AI Visibility Tracker. For Google's AI Overview alone, by keyword and country, use Google AI Overview Tracker.

Use it from code, automations and AI agents

• API: POST https://api.apify.com/v2/acts/zaiq~grok-brand-visibility-tracker/run-sync-get-dataset-items?token=YOUR_TOKEN with the input as JSON. The API tab has Python, JavaScript and cURL examples.
• No code: schedule weekly runs in Apify Console and send rows to Google Sheets, Zapier, Make or n8n from the Integrations tab.
• AI agents (MCP): https://mcp.apify.com?tools=zaiq/grok-brand-visibility-tracker.

Weekly monitoring, competitor gaps and a report

On when a project name is set (the form starts with one), at no extra charge (no new events):

• Project name (projectName): keeps every run's results under that name and compares each run with the last one: mentions gained and lost per question and engine, and competitors that appeared (record CHANGES). Schedule the Actor weekly to follow the movement.
• Report (includeReport): a one-page REPORT.html with the visibility score and its formula, per-engine tables, competitor gaps (the questions where a competitor is named and you are not) and a fix list drawn from the pages the engines cite.

FAQ

Is this what people see in the Grok app? It is xAI's official API with xAI's own web search: the same model and search xAI offers to developers. The consumer app can differ (memory, personalisation, its own interface). This Actor does not log in to or scrape any app.

Why do answers change between runs? AI answers are sampled. Track the same questions weekly with 3 or more runs and watch the mention rate rather than one answer.

How long does an answer take? about a minute.