Active Models

5

5%

Success Rate

99.8%

5%

API Requests

1.2M

5%

Avg Response

124ms

5%

Storage Status

234 GB /500 GB

CPU Usage

35.2 %

33%

Memory Usage

48.2 %

14.2%

Avg Latency (ms)

1254

14.2%

Active Models

05

44.2%

icon

847,392

Total Interactions

33.4%
icon

1.2s

Response Time

24.7%
icon

87.3%

Automation Rate

44.2%
icon

94.7%

Resolution Rate

14.2%

Total AI Requests

2.4M

21%

Last Month

Model Accuracy

15%

21%

Last Month

System Health

99.2%

5%

Last Month

Generated Content

Image Video Audio Text Voice

Agents Status

256

Agents

Active

24

Idle

12

Training

8

Failed

3

Cost Analytics & API Usage

Spending Overview :

$23896

21%
Cost API Usage

Cost Breakdown

Compute

$7965

Storage

$6925

API Call

$4654

Requests by Region

canadaCanada

4569

malaysiaMalaysia

2459

portugalPortugal

1452

Models Usage

GPT-4.1 Llama 3 Mistral Large

Performance Metrics

Accuracy Overtime Inference Latency (ms)

Requests by Category

Image Generator

95K

Video Generator

90K

Audio Generator

80K

Text Generator

60K

Voice Generator

25K

Storage & Requests

50%

Remaining

Requests/sec

1546

GPU Usage

83.5%

Resource Usage (24h)

CPU % Memory % GPU %

Performance Analytics

Interaction

Resolved

Response Time

Fully Automated

74.4%

Human Escalation

25.6%

2.3

Avg Seconds

Automation rate improved by 4,123 interactions