Usage Metrics & AI Gateway
Real-time observability into your AI consumption and Vercel AI Gateway performance
Vercel AI Gateway Integration
Active
Your orchestration layer is routed through Vercel AI Gateway, providing unified caching, rate limiting, and per-token observability across all model providers.
Gateway Status
Operational
Avg Latency
142ms
Cache Hit Rate
24.5%
Token Consumption Breakdown
GPT-4o (Reasoning)
642,891 / 1.0M tokens
Claude 3.5 Sonnet (Coding)
128,400 / 500k tokens
Ollama Local (Metadata Extraction)
Unlimited
Estimated Cost (MTD)
$42.18
-12.4% from last monthActive Workflows