Readily, and it reads them in full rather than skimming. That is the defining property of the engine.

Do you return passage anchors?

Yes, wherever Kimi exposes them.

Kimi citations tracking

kimicitationsAccount required

Kimi cites at document level with passage-level grounding, so a single citation frequently points at one section of a long PDF rather than a page. Nostimates returns both the document and the passage anchor.

How it renders

Document-level references with passage grounding beneath the answer.

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 URL-only citation record loses the passage, and the passage is the point on Kimi. It is the difference between knowing your whitepaper was cited and knowing which section did the work.

What the API returns

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

{
  "engine": "kimi",
  "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=kimi&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 →

Kimi citations FAQ

Does Kimi cite PDFs?: Readily, and it reads them in full rather than skimming. That is the defining property of the engine.
Do you return passage anchors?: Yes, wherever Kimi exposes them.

Find out which sections of your documents get cited

Send your prompt set and document library and we will show you what Kimi actually reads.

Other Kimi 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 →