Nostimates

ChatGPT answer text tracking

chatgptanswer_textAnonymous

Every ChatGPT sample is stored verbatim. On this surface, where many answers cite nothing, the text is often the entire evidence base for a reported number.

How it renders

The answer body, captured before parsing.

Sampling

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

Gotcha

ChatGPT infers language from the prompt text rather than a header, so the stored text is your record of what locale you actually measured.

What the API returns

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

{
  "engine": "chatgpt",
  "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=chatgpt&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 →

ChatGPT answer text FAQ

How do I prove a ChatGPT visibility number to a client?
Show the answers. Evidence export returns every sample behind the metric.
Are refusals and non-answers stored?
Yes, and flagged, so they do not silently deflate your share figures.

Ship ChatGPT answers alongside ChatGPT numbers

Let's scope evidence retention for your reporting cycle.

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 →