For small agencies, two tools stand out: Kanbo#1 keeps client work visible on shared boards, and Orbitly#2 handles planning across several clients.
- mentioned
- no
- rank
- —
- cited
- no
Gemini often reads more pages than it credits. Get its answer as JSON: who it named, in what order, which pages it cited, and the ones it read without citing.
For small agencies, two tools stand out: Kanbo#1 keeps client work visible on shared boards, and Orbitly#2 handles planning across several clients.
sources
0
cited
retrievedPages
4
read
Trellis was read, not named
Read, not credited
Gemini links its sources on some answers only. retrievedPages usually shows what it read anyway, each flagged cited or not, so check both.
answer.sources
suggestedFollowUps
answer.retrievedPages
retrieved true for Trellis, named: no
The request · provider gemini
/chatgpt/ai-rankRank and mention rate over 1–5 answers/chatgpt/visibility-reportShare of voice across prompts and brands/chatgpt/mentionsNamed or not, cited or not, in one answer/chatgpt/prompt-discoveryThe prompts worth tracking/chatgpt/askThe whole answer and its sourcesMCPEvery call is also a tool for your agent$ curl https://api.fetchlayer.dev/chatgpt/mentions \ -H "Authorization: Bearer ss-your-key" \ -d '{ "provider": "gemini", "prompt": "best project management software for small agencies", "targets": [ { "name": "Trellis", "domains": [ "trellis.example" ] }, "Kanbo" ] }'
{
"provider": "gemini",
"targets": [
{
"name": "Trellis",
"mentioned": false,
"mentionCount": 0,
"citedAsSource": false,
"retrieved": true
},
{
"name": "Kanbo",
"mentioned": true,
"mentionCount": 2,
"citedAsSource": false,
"retrieved": true
}
],
"otherBrandsMentioned": [ { "rank": 2, "name": "Orbitly" } ],
"answer": {
"model": "3.5 Flash-Lite",
"sources": [ ],
"searchQueries": null,
"retrievedPages": [
{ "domain": "kanbo.example", "cited": false },
{ "domain": "trellis.example", "cited": false },
…2 more
],
"suggestedFollowUps": [ "Compare Kanbo and Orbitly pricing", … ]
},
"pagesScraped": 1
}
// 1 answer, 1 credit Other assistants
Try it free, buy credits as you go, or take a monthly plan when your volume is steady.
Free
30 requestsYou pay
$0
Pay as you go
never expireYou pay
$1.99per 1,000
Monthly plan
Starter15,000
You pay
$25per month
Not sure which volume fits?
15 minutes with the founder. Tell us the workload, we tell you what it needs.
Guaranteed throughput on the platform you run on
A dedicated platform from $400/mo, plus $500 for each ~21 req/s. Every other platform on the same key. 99.95% uptime, 24-hour support on Slack or Telegram.
FAQ · Gemini
No. Google’s Gemini API gives you a model for your own app. This gives you what Gemini answers people about your market: the brands it names, the order it puts them in, the pages it cites and the pages it read, as JSON. You don’t need a Google account or key, only a FetchLayer key. FetchLayer is not affiliated with, endorsed by, or sponsored by Google.
No. Gemini picks the model. answer.model reports the one Gemini names for the answer, for example “3.5 Flash-Lite”, so you can see when it changes.
Gemini searches the web for most prompts but links its sources on some answers only. When sources is empty, retrievedPages is usually still filled: the pages Gemini read for the answer, each flagged cited or not. Check both before you conclude a page played no part.
Every page Gemini looked at for the answer, with url, title, domain and cited. A target’s retrieved is true when one of its pages is among them, even if the answer neither names nor cites it. That is the page closest to winning: it was read, and someone else got the credit.
Gemini does not show them, so searchQueries is always null for gemini. retrievedPages is the closer signal: what it read, not what it typed.
The answer’s language and currency follow the prompt, not the country. servedCountry is the location Gemini itself states for the answer, when it says so, and null otherwise. To see a market, name it in the prompt.
No. Gemini, AI Overviews and AI Mode are three different Google products with different answers. This is Gemini. AI Overviews and AI Mode are on our coming-soon list and will take the same request.
FetchLayer's Gemini visibility API returns Gemini answers, the brands they mention, the pages they cite and the pages they read, and your rank among the recommendations as JSON over REST or MCP. A request is one Gemini answer, and each request costs one credit: $1.99 per 1,000 requests pay-as-you-go, or $25 a month for 15,000, with 30 free requests and no card to start. A request that fails is not billed. The same key covers 36 other platforms, and every route is also a tool on FetchLayer's MCP server at https://mcp.fetchlayer.dev, for Claude, ChatGPT, Cursor and other MCP clients.
FetchLayer is not affiliated with, endorsed by, or sponsored by OpenAI, Microsoft or any other assistant named here. Brands in the examples are invented.