🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
Endpoints
Manage deployed model inference endpoints.
🌐
1,635
Total
✅
8,840
Healthy
⚠️
9,576
Degraded
❌
1,902
Down
| Name | Status | Model | Replicas | RPS | Latency P99 | GPU Type | |
|---|---|---|---|---|---|---|---|
| multimodal-canary-v2 | Stopped | llama-3.1-70b | 3 | 3,670 | 1331ms | A10-24G | |
| multimodal-prod-v2 | Error | llama-3.1-70b | 4 | 1,767 | 400ms | A10-24G | |
| llm-prod-v3 | Active | whisper-large | 3 | 845 | 1922ms | H100-80G | |
| llm-staging-v2 | Stopped | whisper-large | 8 | 491 | 1752ms | A100-80G | |
| embedding-canary-v1 | Active | llama-3.1-70b | 1 | 1,188 | 1397ms | A10-24G | |
| llm-staging-v4 | Scaling | stable-diffusion-xl | 7 | 3,094 | 173ms | A100-80G | |
| audio-prod-v1 | Stopped | mistral-7b | 7 | 2,654 | 766ms | H100-80G | |
| embedding-prod-v1 | Active | whisper-large | 2 | 3,483 | 1992ms | A10-24G | |
| multimodal-canary-v1 | Error | whisper-large | 3 | 2,612 | 1701ms | A100-80G | |
| multimodal-staging-v5 | Active | mistral-7b | 7 | 2,627 | 1694ms | A10-24G |