Monitor Google Vertex AI with Respan
Overview
Respan routes Google Vertex AI model calls through the gateway, providing unified observability including logs, cost tracking, latency metrics, and reliability monitoring.
Configure your Google Cloud credentials in the Respan dashboard or pass them per-request. Compatible with supported gateway frameworks.
How it works
Add your Google Vertex AI credentials in the Respan Providers dashboard.
Route requests through the Respan gateway. Every call is logged with token usage, cost, and latency.