Usage
Per-request telemetry for calls to your deployed models. Filter by API key, deployment, model, status, and time range.
Usage by key
Total requests
3
all time
Total tokens
17.7k
all time
Avg latency
1.7s
all time
| Key | Requests | Error % | Total Tokens ↓ | Avg Latency | p95 Latency | Last Used |
|---|---|---|---|---|---|---|
| lorena-d155-openai-proxy | 3 | 0.0% | 17.7k | 1.7s | 3.4s | 20 may 2026, 16:35 |
Requests
| Time | API key | Deployment | Model | Status | Streamed | Latency |
|---|---|---|---|---|---|---|
| 20 may 2026, 16:35 | DEPLOYMENTlorena-d155-openai-proxy | base-d155-Qwen3.6-35B-A3B | Qwen/Qwen3.6-35B-A3B | 200 | Yes | 3.4s |
| 20 may 2026, 15:49 | DEPLOYMENTlorena-d155-openai-proxy | base-d155-Qwen3.6-35B-A3B | Qwen/Qwen3.6-35B-A3B | 200 | No | 84s |
| 19 may 2026, 11:50 | DEPLOYMENTlorena-d155-openai-proxy | base-d155-Qwen3.6-35B-A3B | Qwen/Qwen3.6-35B-A3B | 200 | No | 56s |
Page totals (3 rows)
Showing page 1 of 1 pages