Google AI Mode sources tracking
AI Mode's right-hand panel is the widest source set Google exposes anywhere, because it aggregates across every fan-out branch. It is the closest thing to seeing what the model actually read.
How it renders
A persistent right-hand source panel grouped loosely by sub-question.
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 Google AI Mode for the sources field, sampled n times and returned as one object per prompt.
{
"engine": "google_ai_mode",
"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 →Google AI Mode sources FAQ
- Why is the AI Mode source panel wider than the inline citations?
- Fan-out consults far more pages than the synthesised answer credits inline.
- Can you attribute a source to a specific sub-question?
- Partially, where the panel grouping is legible. We return the grouping when present and flag it when it is not.
See everything AI Mode consulted
The panel is the richest source data on any Western engine. We'll set up collection across your prompt set.
Other Google AI Mode data
Across every engine
Compare how sources behaves on every engine we track.
Sources across all engines →