API reference · Observability
Logs and analytics
Every request that passes through the gateway is logged: provider, model, tokens, cost, latency, cache, guardrail and tool-scan results. Search the logs, read one in full, chart usage over time, break it down, and export it.
- Get a usage breakdownGET
/v1/analytics/breakdown - Get the latency graphGET
/v1/analytics/latency - Get usage totalsGET
/v1/analytics/summary - Get a usage time seriesGET
/v1/analytics/timeseries - Search request logsGET
/v1/logs - Get a request logGET
/v1/logs/{id} - Start a log exportPOST
/v1/logs/export - Get a log exportGET
/v1/logs/export/{jobId} - Download a log exportGET
/v1/logs/export/{jobId}/download
VectorAxis is built by GK Labs, a member of NVIDIA Inception.
© 2025 NVIDIA, the NVIDIA logo, and NVIDIA Inception are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries.