🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
Public Endpoints
Manage publicly accessible inference endpoints across the platform.
globe
3,724
Total Endpoints
check-circle
9,860
Active
pause
8,700
Paused
activity
7,144
Avg Latency
| Endpoint Name | Model | Version | Replicas | RPM | P99 Latency | Status | Created | |
|---|---|---|---|---|---|---|---|---|
| multimodal-prod-v1 | mistral-7b | | 7 | 1703ms | Active | 2026-02-07 | ||
| multimodal-prod-v4 | llama-3.1-70b | | 2 | 1144ms | Active | 2026-02-15 | ||
| vision-staging-v1 | whisper-large | | 6 | 1049ms | Scaling | 2026-01-07 | ||
| vision-staging-v2 | mistral-7b | | 8 | 1894ms | Scaling | 2026-01-17 | ||
| llm-prod-v4 | stable-diffusion-xl | | 1 | 323ms | Active | 2026-02-10 | ||
| multimodal-prod-v3 | llama-3.1-70b | | 2 | 504ms | Stopped | 2026-01-10 | ||
| audio-staging-v2 | mistral-7b | | 3 | 880ms | Stopped | 2026-02-11 | ||
| multimodal-prod-v2 | mistral-7b | | 1 | 1602ms | Scaling | 2026-02-09 | ||
| multimodal-staging-v1 | stable-diffusion-xl | | 3 | 306ms | Active | 2026-01-08 | ||
| multimodal-staging-v4 | mistral-7b | | 6 | 1859ms | Active | 2026-02-12 |