🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
Public Endpoints
Manage publicly accessible inference endpoints across the platform.
globe
1,214
Total Endpoints
check-circle
3,133
Active
pause
6,271
Paused
activity
4,328
Avg Latency
| Endpoint Name | Model | Version | Replicas | RPM | P99 Latency | Status | Created | |
|---|---|---|---|---|---|---|---|---|
| llm-staging-v2 | llama-3.1-70b | | 8 | 1773ms | Stopped | 2026-04-03 | ||
| vision-prod-v4 | whisper-large | | 2 | 266ms | Error | 2026-04-05 | ||
| embedding-canary-v5 | mistral-7b | | 6 | 1817ms | Scaling | 2026-03-10 | ||
| llm-staging-v1 | llama-3.1-70b | | 4 | 1584ms | Scaling | 2026-03-29 | ||
| multimodal-canary-v1 | whisper-large | | 2 | 482ms | Stopped | 2026-02-28 | ||
| multimodal-canary-v4 | mistral-7b | | 8 | 1769ms | Active | 2026-02-14 | ||
| audio-canary-v4 | whisper-large | | 2 | 343ms | Error | 2026-04-08 | ||
| embedding-prod-v4 | stable-diffusion-xl | | 1 | 815ms | Stopped | 2026-02-25 | ||
| multimodal-prod-v5 | whisper-large | | 2 | 82ms | Active | 2026-03-08 | ||
| embedding-prod-v3 | stable-diffusion-xl | | 3 | 786ms | Active | 2026-03-31 |