Qwen sources tracking
The full Qwen source set shows how much of an answer comes from inside Alibaba's own properties versus the open Chinese web — which is usually the most actionable single fact about the engine.
How it renders
Inline sources plus, where present, an expanded reference set.
Sampling
Source panels are wider and more stable than inline citations, so they reach a usable confidence interval at lower n.
Gotcha
What the API returns
A single collection call against Qwen for the sources field, sampled n times and returned as one object per prompt.
{
"engine": "qwen",
"field": "sources",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"sources": [
{
"url": "https://nostimates.com/docs",
"domain": "nostimates.com",
"inline": true,
"sample_frequency": 0.7
},
{
"url": "https://example.org/report",
"domain": "example.org",
"inline": false,
"sample_frequency": 0.23
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| url | string | Source URL from the panel. |
| domain | string | Registrable domain. |
| title | string | null | Panel title as rendered. |
| inline | boolean | Whether this source was also cited inline. |
| sample_frequency | float | Share of n samples containing this source. |
What it costs
Included in the base collection wherever the engine exposes a panel.
See credit pricing →Qwen sources FAQ
- How concentrated are Qwen's sources?
- More than any Western engine on commercial prompts. We tag ecosystem domains so you can quantify it.
- Does that mean off-Alibaba content is wasted?
- Not wasted, but weaker on commerce prompts than it would be on Baidu or Naver.
Quantify Alibaba concentration in your category
We will run a sample and show the ecosystem-versus-open-web split for your prompts.
Other Qwen data
Across every engine
Compare how sources behaves on every engine we track.
Sources across all engines →