🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
Endpoints
Manage deployed model inference endpoints.
🌐
2,800
Total
✅
1,216
Healthy
⚠️
9,752
Degraded
❌
9,888
Down
| Name | Status | Model | Replicas | RPS | Latency P99 | GPU Type | |
|---|---|---|---|---|---|---|---|
| vision-prod-v2 | Active | stable-diffusion-xl | 2 | 2,788 | 602ms | A10-24G | |
| llm-staging-v3 | Scaling | whisper-large | 4 | 2,647 | 284ms | A100-80G | |
| multimodal-canary-v1 | Scaling | whisper-large | 3 | 4,488 | 1587ms | A100-80G | |
| llm-canary-v5 | Error | mistral-7b | 4 | 1,694 | 540ms | A100-80G | |
| multimodal-canary-v3 | Error | mistral-7b | 5 | 2,552 | 1705ms | A10-24G | |
| audio-staging-v2 | Scaling | llama-3.1-70b | 8 | 1,846 | 354ms | H100-80G | |
| llm-canary-v2 | Scaling | mistral-7b | 4 | 2,176 | 133ms | H100-80G | |
| vision-staging-v2 | Error | whisper-large | 5 | 4,399 | 246ms | H100-80G | |
| embedding-prod-v1 | Scaling | whisper-large | 6 | 697 | 160ms | H100-80G | |
| llm-canary-v5 | Stopped | whisper-large | 2 | 893 | 530ms | A100-80G |