AI Visibility API for GEO Monitoring

Build AI brand visibility tracking with scheduled prompts, mentions, citations and competitor share of voice. Connect GEO monitoring to your product via API.

Start free Read the docs ↗

Repeat a consistent set of questions

Save brand aliases, tracked domains, competitors, engines, prompts and a country. The monitor runs them every 1-168 hours. Keep the prompt set and engines fixed to compare periods on the same basis.

Separate mentions, citations and competitive share

Mentions match brand aliases in answer text; citations match registered domains in the source list. Compare per-engine mention rates and competitive share within the collected answers.

How to track your brand in ChatGPT

The example below runs the same prompt daily across ChatGPT and Gemini. Keep category discovery prompts separate from direct brand comparisons. Register the Korean and English brand names as aliases when both are used, and add the official sites you want to track to domains.

AI visibility metrics available through the API

Use GET /v1/monitors/:id for legacy detail statistics and GET /v1/monitors/:id/analytics for report metrics. Keep their response structures and denominators distinct, and inspect the underlying answers and sources alongside aggregates.

engineRates: compare mention and citation results by engine.
topDomains, topPages: inspect cited domains and individual pages.
Legacy detail shareOfVoice contains runs and brands[].mentions. Compute each independent mention rate as mentions ÷ runs × 100.
Analytics brands[].mentionRate is brand mentions ÷ answers scored for that brand × 100. brands[].shareOfVoice is brand mentions ÷ all tracked brand mentions × 100; shares sum to 100% when the denominator is positive. Unavailable samples or comparison conditions are represented by null.

Create a monitor

Send this input to POST /v1/monitors. Replace the illustrative brand and domain with your actual tracking target. You can also create, edit and pause monitors in the dashboard.

JSON

{
  "name": "Earbud brand tracking",
  "engines": [
    "CHATGPT",
    "GEMINI"
  ],
  "prompts": [
    "best wireless earbuds for commuting"
  ],
  "aliases": [
    "Acme Audio"
  ],
  "domains": [
    "example.com"
  ],
  "competitors": [
    {
      "name": "Sony",
      "aliases": [
        "Sony"
      ]
    }
  ],
  "country": "US",
  "intervalHours": 24
}

Scheduled runs use ordinary task limits

With one sample and one location, 12 prompts across ChatGPT and Google AI Overviews create 24 tasks, with a base cost of 27 credits if all complete. Competitor read adds 80 credits per monitor per 30 days, split across runs by cadence and charged when all tasks in a run have been submitted. Thirty daily runs cost about 890 credits: 810 for tasks plus 80 for competitor read. analysis: true adds 1 credit per analyzed answer. Scheduled work uses your concurrency and balance; correlate independently completed results by task.id.

Answers and sources from the period a rate changed

Open that period's answers and sources, and check whether the prompt set or AI summary appearance changed too. Register your brand domains to track domain citations.