All systems healthy
Inferix Labs24h window

Inference

Throughput, latency, and spend across owned models and providers.

Requests (24h)

18,330

all models · all tenants+6.2%

Throughput

764 / hr

rolling average+3.1%

P95 latency

842 ms

inference wall time−42ms

Error rate

0.6%

non-success status−0.1%

Tokens (24h)

6.1M

prompt + completion+4.8%

Cost (24h)

$22.61

LensAI cost_usd+1.4%

Hourly throughput

UTC · today

06:00
07:00
08:00
09:00
10:00
11:00
12:00
13:00
14:00
15:00

By model

24h

ModelReqsAvgP95ErrCost
slm-support-v26,200280ms540ms0.3%$2.40
general-llm-v34,100420ms780ms0.4%$6.80
slm-apiheal-v13,180210ms390ms0.2%$1.60
claude-sonnet2,850510ms920ms0.8%$8.40
gpt-4o2,000390ms710ms0.5%$3.41