Qwen answer text tracking
qwenanswer_textAccount required
Qwen answers are stored verbatim in Chinese with the intent split recorded, so commercial and informational behaviour can be reported separately with evidence.
How it renders
The 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
Commercial and informational answers from Qwen barely resemble each other. Storing them in one undifferentiated bucket makes the averages meaningless.
What the API returns
A single collection call against Qwen for the answer text field, sampled n times and returned as one object per prompt.
{
"engine": "qwen",
"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"
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| text | string | Verbatim answer, markup stripped. |
| html | string | Original markup, for citation position reconstruction. |
| tokens | integer | Approximate length, useful for drift detection. |
| captured_at | timestamp | UTC collection time for this sample. |
| sample_index | integer | Which of the n samples this is. |
What it costs
Included. Evidence retention defaults to 90 days and is configurable.
See credit pricing →Qwen answer text FAQ
- Do you tag intent?
- Yes, at prompt-set level, configured with you rather than inferred.
- Is the original language preserved?
- Always. Translation happens at report time if at all.
Keep Qwen evidence split by intent
We will structure your prompt set so commerce and information do not contaminate each other.
Other Qwen data
Across every engine
Compare how answer text behaves on every engine we track.
Answer text across all engines →