Llama3

Deployment dpl-d4e5f6

Back to Deployments

TU

Llama3

Active

https://nexus.trinidy.cloud/v1/llama3/inference

Requests 24h

56.8K

Avg Latency

88ms

Uptime

99.95%

Region

eu-west-1

Instance

nexus.gpu.a10g

Cost/hr

$2.10

Total Requests

206.6K

Total Tokens

57.9M

Total Errors

90

0.044% error rate

Cost (24h)

$50.40

Requests per Hour

Average Latency (ms)

Errors per Hour

Tokens Generated