Research
Time Range:
INPUT TOKENS
Input Tokens
OUTPUT TOKENS
Output Tokens
TOKENS/S (THROUGHPUT)
Tokens/Second
TTFT (LATENCY)
seconds
RUNS
Total Runs
Utilization Over Time
—
avg busy
% of instance capacity busy over the selected period. <75% · 75–90% · ≥90% maxed out.
Total Invocations
194.43K
Active Instances
1
Compute Multiplier
17.72x
Deployment
Template
vllm
Revision
7eb21d27…047b
Concurrency
60
Max Instances
—
Scaling Threshold
—
Shutdown After
—
Preemptible
Yes
External Egress
Blocked
Hardware
GPU Count
8
Min VRAM/GPU
16 GB
GPU Include
h200
GPU Exclude
—
Instances
| Instance ID | Region | Status | Verified | Last Verified |
|---|---|---|---|---|
| n/a | Active | 8/30/2026, 1:58:45 PM |