Available now
Token counts in response
cached_tokens enables prompt caching discounts later.
Error codes
Full details: Errors & Rate Limits
Rate limit headers
Dashboard
The control panel provides:- API keys — create and delete keys
- Usage — token limit and token counter by model, next reset time
- Recent requests — last few API requests and responses
Coming soon
Response headers
x-forii-region lets you verify your requests are served from India, not routed to US servers. Indian jurisdiction applies to all request data — no US CLOUD Act exposure.CLI observability
Request annotations
Planned
Advanced dashboard
- Latency percentiles (p50/p90/p99) by model
- Error rate trends
- Cache hit rate visualization
- Rate limit utilization
- Region breakdown
- Annotations filtering
- CSV/JSON export
Prometheus metrics endpoint
External integrations
Related
- Usage API — Programmatic access to usage data
- Errors & Rate Limits — Error codes and headers
- Dashboard — Usage and requests in the UI