Duck.ai Visibility API — Brand Mentions per Model (GPT, Claude, Mistral, Gemma) | FetchLayer

Which model
recommends you?

Duck.ai lets you choose the model. Ask GPT Luna, Claude Haiku, GPT mini, Mistral Small, gpt-oss and Gemma the same question, one request per model, and see which of them name you, as JSON.

prompt best project management software for small agencies provider duck_ai target Trellis
Duck.aimodel Claude Haiku

Three tools come up most for small agencies: Trellis#1 for retainer work, with a budget per client. Kanbo#2 for client-facing boards. Fieldnote#3 if your team works mostly in docs.

mentioned
yes
rank
#1
cited
#2
Same prompt, every model6 requests
  1. GPT Luna #2
  2. Claude Haiku #1
  3. GPT mini not named
  4. Mistral Small #3
  5. gpt-oss #1
  6. Gemma not named
named by
4/6
best rank
#1
answer.model
per answer
6
models to choose from
answer.model
the model that answered
on
web search, except Mistral Small
1
credit per answer

Under the answer

The next questions your buyers see.

Duck.ai shows related searches under its answers. They come back as suggestedFollowUps: the prompts worth tracking next.

answer · model Claude Haiku

Three tools come up most for small agencies: Trellis for retainer work, Kanbo for client-facing boards, Fieldnote for teams in docs.

searchQueries

  • project management software small agencies

suggestedFollowUps

Track these next with the same request.

The request · provider duck_ai

Five calls, one key, the same shape for every assistant.

  • /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 sources
  • MCPEvery call is also a tool for your agent
Request
$ curl https://api.fetchlayer.dev/chatgpt/ai-rank \
  -H "Authorization: Bearer ss-your-key" \
  -d '{
    "provider": "duck_ai",
    "model": "claude-haiku",
    "prompt": "best project management software for small agencies",
    "target": "Trellis",
    "competitors": [ "Kanbo", "Fieldnote" ],
    "runs": 3
  }'
Response
{
  "provider": "duck_ai",
  "model": "Claude Haiku",
  "aggregate": {
    "runs": 3,
    "mentionRate": 100,
    "averageRank": 1.3,
    "bestRank": 1,
    "worstRank": 2,
    "citationRate": 67
  },
  "competitorAggregates": [
    { "name": "Kanbo", "mentionRate": 100, "averageRank": 2 },
    { "name": "Fieldnote", "mentionRate": 67, "averageRank": 3 }
  ],
  "runs": [
    {
      "rank": 1,
      "mentioned": true,
      "citationRank": 2,
      "method": "numbered_list"
    },
    …2 more
  ],
  "pagesScraped": 3
}
// 3 answers, 3 credits

Other assistants

Same request, every assistant.

Start free. Scale when ready.

Try it free, buy credits as you go, or take a monthly plan when your volume is steady.

Free

30 requests
  • Every platform and endpoint
  • REST and MCP
  • No credit card

You pay

$0

30 req × $0
$0
credit card
none
Start free

Pay as you go

never expire
  • No monthly commitment
  • Same access as subscribers
  • ∞ req/min, ∞ API keys

You pay

$1.99per 1,000

1,000 req × $1.99/1k
$1.99
monthly fee
$0
expires
never
Get API key

Monthly plan

Starter

15,000

  • ∞ req/min, ∞ API keys

You pay

$25per month

15,000 req × $1.67/1k
$25/mo
on credits × $1.99/1k
$29.85
you save
$4.85/mo
Get started
  • One page fetched costs one credit.
  • A request that returns no usable data costs 0 credits.
Not sure? Book a 15-min call

Not sure which volume fits?

15 minutes with the founder. Tell us the workload, we tell you what it needs.

Book a call

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.

Build your plan

FAQ · Duck.ai

Common questions.

Is this a Duck.ai chat API?

No. It does not give you a chat model for your own app. It tells you what Duck.ai answers people about your market: the brands it names, the order it puts them in and the pages it cites, as JSON. FetchLayer is not affiliated with, endorsed by, or sponsored by DuckDuckGo.

Which models can I choose?

Set model on any of the five calls with provider duck_ai. GET /chatgpt/providers lists the models Duck.ai offers, with the default used when you set none. answer.model reports the model that wrote each answer, as Duck.ai names it, and an answer from any other model than the one you asked for is never returned.

Can I compare models in one request?

No: one request asks one model. To compare, send the same prompt once per model on the same key and read the results side by side. Every answer is billed the same, one credit, whichever model wrote it.

Does the answer change by country?

No. Duck.ai answers as for the U.S. unless the prompt names a country, and outside the US notes says so. servedCountry is the country the answer was asked from. To see a market, put it in the prompt.

Does Duck.ai search the web?

With every model that can: those are asked with web search on whether webSearch is auto or on. answer.usedWebSearch and answer.searchQueries report the search it ran. Mistral Small answers from its own knowledge, without searching and with no sources, and webSearch "on" with it is a 400.

What is suggestedFollowUps?

The related searches Duck.ai shows under an answer, returned as answer.suggestedFollowUps. They are what a buyer is offered next, so they are good prompts to track.

Is this DuckDuckGo search results?

No, this is Duck.ai’s written answer. For DuckDuckGo’s results pages and rank checks, see the DuckDuckGo Search API on the same key.

How much does it cost?

FetchLayer's Duck.ai visibility API returns Duck.ai answers per model, the brands they mention, the pages they cite and your rank among the recommendations as JSON over REST or MCP. A request is one Duck.ai 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.

Find out what Duck.ai says about you.