Baidu ERNIE answer text tracking
baidu_ernieanswer_textAnonymous
Every Baidu AI answer is stored verbatim in Chinese, which on the highest-volume Chinese surface is what turns a share figure into something a client can check.
How it renders
The SERP AI answer block, 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
Baidu rewrites its AI answers frequently without changing the link set. Text storage is the only way to show a client that framing moved while sourcing did not.
What the API returns
A single collection call against Baidu ERNIE for the answer text field, sampled n times and returned as one object per prompt.
{
"engine": "baidu_ernie",
"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 →Baidu ERNIE answer text FAQ
- Is every sample stored?
- Yes, in Chinese, with translation only at report time.
- Retention?
- Ninety days by default, configurable.
Ship the Chinese sentence with the Chinese number
We will scope verbatim retention across your Baidu prompt set.
Other Baidu ERNIE data
Across every engine
Compare how answer text behaves on every engine we track.
Answer text across all engines →