Citations tracking across AI answer engines
Citation tracking across AI answer engines means recording which URLs each engine links from its answer, on every sample, for every prompt. Nostimates returns citations per engine with domain, position and sample frequency, so you can report citation share with a confidence interval rather than a single reading.
How it differs by engine
Citations surface as linked chips, numbered footnotes or an expandable source list depending on the engine.
Google AI Overviews citations
A horizontal carousel of link chips pinned to the top-right of the summary block, plus inline links inside the summary sentences.
google_ai_overviews
Google AI Mode citations
Inline linked phrases inside the answer plus a right-hand source panel.
google_ai_mode
ChatGPT citations
Inline link pills within the answer, plus an expandable source list beneath it.
chatgpt
Perplexity citations
Numbered inline markers mapped to a stable, ordered source list.
perplexity
Microsoft Copilot citations
Numbered footnote links rendered beneath the answer body.
copilot
Gemini app citations
Grounding chips beneath the answer plus a sources drawer that opens on demand.
gemini
DeepSeek citations
A numbered reference list under search-enabled answers; absent on pure-model answers.
deepseek
Qwen citations
Inline source links within search-augmented answers.
qwen
Doubao citations
Card-style source references beneath the answer, weighted to ByteDance properties.
doubao
Kimi citations
Document-level references with passage grounding beneath the answer.
kimi
Baidu ERNIE citations
Source links embedded in the AI answer block on the Baidu results page.
baidu_ernie
Naver citations
Blog, cafe and knowledge-base references shown alongside web sources.
naver
Sampling
What the API returns
{
"engine": "google_ai_overviews",
"field": "citations",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"citations": [
{
"url": "https://nostimates.com/engines",
"domain": "nostimates.com",
"position": 1,
"sample_frequency": 0.63
},
{
"url": "https://example.org/guide",
"domain": "example.org",
"position": 3,
"sample_frequency": 0.4
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| url | string | Absolute URL as the engine rendered it, redirects resolved. |
| domain | string | Registrable domain, normalised for grouping. |
| position | integer | Order within the citation set for that sample. |
| sample_frequency | float | Share of the n samples in which this URL appeared. |
| anchor_text | string | null | Visible anchor or chip label, when the engine renders one. |
| first_seen | date | First run in which this URL appeared for this prompt. |
Citations FAQ
- What is citations tracking?
- Citation tracking across AI answer engines means recording which URLs each engine links from its answer, on every sample, for every prompt. Nostimates returns citations per engine with domain, position and sample frequency, so you can report citation share with a confidence interval rather than a single reading.
- How is citations sampled?
- Citation sets are the least stable field we return. The same prompt run n times will produce overlapping but non-identical URL sets, which is why we report frequency across samples rather than a list from one run.
- What does citations cost?
- 1 credit per prompt per sample. Citations are included in the base collection — no surcharge.
Get citations on your prompt set
Track it in the dashboard or pull it in through the API. Send us the prompts, the brands and the markets, and we'll come back with a per-engine coverage plan and the credit arithmetic behind it.