Google Vertex AI Monitoring & Tracing
Auto-instrument enterprise Vertex AI model calls with zero code changes. Get full span trees, cost at Vertex AI's billed rates, and security scanning on every generation request.
Free tier · No credit card · 2-minute setup
What you get with Fluiq for Google Vertex AI
Enterprise-grade traces
Vertex AI GenerativeModel calls are traced with full span trees, input/output token counts, latency, and safety rating metadata captured on every request.
Cost at Vertex rates
API costs attributed at Vertex AI's published per-character and per-token rates for each model, surfaced per trace and in aggregate cost analytics.
Security scanning
Prompt injection and PII detection run on every Vertex AI call before responses reach your application, blocking attacks that bypass Google's built-in safety filters.
Add Fluiq to your Google Vertex AI app in 2 lines
import fluiq
fluiq.instrument(api_key="fl_...") # patches vertexai automatically
import vertexai
from vertexai.generative_models import GenerativeModel
vertexai.init(project="my-gcp-project", location="us-central1")
model = GenerativeModel("gemini-1.5-pro")
# Traced automatically with cost at Vertex AI rates:
response = model.generate_content("Summarise this enterprise document")
# Async is also traced:
response = await model.generate_content_async("Explain AI observability")What Fluiq instruments in Google Vertex AI
Every call to these methods is automatically traced, no decorators, no wrappers, no manual spans.
vertexai.generative_models.GenerativeModel.generate_content()vertexai.generative_models.GenerativeModel.generate_content_async()vertexai.generative_models.GenerativeModel.stream()vertexai.language_models.TextGenerationModel.predict()vertexai.language_models.TextEmbeddingModel.get_embeddings()Start tracing Google Vertex AI in 2 minutes
Free tier. No credit card. Full traces, security scanning, and evals on your first Google Vertex AI call.
Unlimited free traces · 1,000 evals / month · 14-day retention