AIVercel5 months ago
Live model performance metrics accessible via AI Gateway
2 min read
AI Gateway now displays live throughput and latency metrics across hundreds of models. The model list includes sortable columns for P50 latency and throughput, updated hourly. A REST API provides programmatic access to P50 and P95 latency and throughput per provider.
Level
Hype check
Tap to vote and see what everyone thinks.