🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
Endpoints
Manage deployed model inference endpoints.
🌐
6,431
Total
✅
3,310
Healthy
⚠️
6,143
Degraded
❌
461
Down
| Name | Status | Model | Replicas | RPS | Latency P99 | GPU Type | |
|---|---|---|---|---|---|---|---|
| llm-staging-v2 | Active | whisper-large | 1 | 4,400 | 1477ms | A100-80G | |
| llm-prod-v5 | Stopped | llama-3.1-70b | 3 | 1,322 | 1556ms | H100-80G | |
| multimodal-staging-v2 | Error | llama-3.1-70b | 4 | 634 | 1306ms | A100-80G | |
| llm-canary-v1 | Error | whisper-large | 4 | 4,910 | 60ms | A100-80G | |
| embedding-prod-v5 | Active | whisper-large | 2 | 4,969 | 176ms | H100-80G | |
| llm-staging-v2 | Error | whisper-large | 2 | 2,358 | 1309ms | A100-80G | |
| vision-prod-v2 | Scaling | whisper-large | 3 | 933 | 1226ms | A10-24G | |
| llm-canary-v1 | Stopped | mistral-7b | 2 | 1,048 | 995ms | H100-80G | |
| vision-staging-v5 | Scaling | llama-3.1-70b | 5 | 237 | 918ms | H100-80G | |
| multimodal-canary-v1 | Scaling | mistral-7b | 2 | 1,832 | 1054ms | H100-80G |