Nostimates

Kimi answer text tracking

kimianswer_textAccount required

Kimi answers are long, and we store them whole. Truncating them would discard the passages that explain why a brand was framed the way it was.

How it renders

The full answer body, stored unmodified.

Sampling

Every sample is stored, not just the modal one. Divergence between samples is the raw material for the volatility metrics.

Gotcha

Storage cost is higher here because the answers are genuinely long. We do not truncate to save space, because the tail of a Kimi answer is often where the competitor comparison lives.

What the API returns

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

{
  "engine": "kimi",
  "field": "answer_text",
  "prompt": "best ai visibility tracking tool",
  "country": "GB",
  "language": "en",
  "n": 30,
  "samples": [
    {
      "sample_index": 1,
      "tokens": 214,
      "text": "Several APIs return AI answer data…",
      "captured_at": "2026-08-03T09:14:22Z"
    }
  ]
}
GET /v1/collect?engine=kimi&field=answer_text

Response fields

KeyTypeNotes
textstringVerbatim answer, markup stripped.
htmlstringOriginal markup, for citation position reconstruction.
tokensintegerApproximate length, useful for drift detection.
captured_attimestampUTC collection time for this sample.
sample_indexintegerWhich of the n samples this is.

What it costs

Included. Evidence retention defaults to 90 days and is configurable.

See credit pricing →

Kimi answer text FAQ

Are long answers truncated?
No. The end of a Kimi answer frequently carries the comparison you care about.
Does retention differ?
Same ninety-day default, configurable.

Keep Kimi answers whole

We will scope full-text retention across your Kimi collection.

No newsletter. One reply from a human.

Across every engine

Compare how answer text behaves on every engine we track.

Answer text across all engines →