DeepSeek sources tracking
Where DeepSeek runs search, its full source set skews toward Chinese-language properties that Western tooling does not index at all. Nostimates returns the whole list with domains normalised for Chinese hosting patterns.
How it renders
A reference block beneath search-enabled answers.
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 DeepSeek for the sources field, sampled n times and returned as one object per prompt.
{
"engine": "deepseek",
"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 →DeepSeek sources FAQ
- What kinds of sources dominate DeepSeek?
- Chinese-language encyclopaedic and forum properties far more than Western media. Wikipedia presence still predicts mention rate strongly.
- How do you group Chinese domains?
- Registrable domain plus a curated publisher map for the large multi-subdomain platforms.
See the Chinese source graph behind your category
We will run a sample and show you which properties actually feed DeepSeek for your prompts.
Other DeepSeek data
Across every engine
Compare how sources behaves on every engine we track.
Sources across all engines →