ChatSample
Usage
Headline totals, then volume, routing, and grounding. Sample figures only. Not AWS infrastructure consumption, and not a live model.
Scope: 30 days · All workspaces · sample figures
AI requests
68
Fictional requests
Success rate
99%
Retrieval hits
59%
Grounded answers
54%
Share asked to cite, in this sample
Input tokens
271,000
Output tokens
82,400
Avg latency
501 ms
Most-used model
Fictional Local 3B
By workspace
| Workspace | Requests | Input tokens | Output tokens |
|---|---|---|---|
| Northwind Harbor | 42 | 210,000 | 70,000 |
| Paperkite Studio | 17 | 44,000 | 9,000 |
| Example Goods | 9 | 17,000 | 3,400 |