Does ChatGPT always cite sources?

Only when the answer is web-search-backed. Pure-model answers cite nothing, and we mark those samples explicitly rather than counting them as zero citations.

Why not log in for better data?

Because logged-in data is personalised and irreproducible. Identity-free collection is the methodology, not a limitation.

ChatGPT citations tracking

chatgptcitationsAnonymous

ChatGPT returns citations on web-search-backed answers as inline link pills and an expandable source list. We collect logged-out, so the citation set is the one an anonymous user would see, not one shaped by somebody's account history.

How it renders

Inline link pills within the answer, plus an expandable source list beneath it.

Sampling

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.

Gotcha

A signed-in session carries memory and personalisation. A citation number measured through somebody's account is a number nobody else can reproduce, which is why we never log in.

What the API returns

A single collection call against ChatGPT for the citations field, sampled n times and returned as one object per prompt.

{
  "engine": "chatgpt",
  "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
    }
  ]
}

GET /v1/collect?engine=chatgpt&field=citations

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.

What it costs

1 credit per prompt per sample. Citations are included in the base collection — no surcharge.

See credit pricing →

ChatGPT citations FAQ

Does ChatGPT always cite sources?: Only when the answer is web-search-backed. Pure-model answers cite nothing, and we mark those samples explicitly rather than counting them as zero citations.
Why not log in for better data?: Because logged-in data is personalised and irreproducible. Identity-free collection is the methodology, not a limitation.

Track ChatGPT citations the way an anonymous user sees them

Send your prompt set and we'll price logged-out ChatGPT collection across your markets.

Other ChatGPT data

Brand mentions Sources Answer text Share of voice Sentiment Prompt volatility Position Locale variance

Across every engine

Compare how citations behaves on every engine we track.

Citations across all engines →