All posts tagged

Build a low-cardinality APISIX monitoring path with a private Prometheus scrape, service dashboards, SLO-oriented queries, and actionable alerts.

Build LLM monitoring with Prometheus using terminal request outcomes, streaming latency, TTFT, fallback, and policy signals from AISIX 1.6.0.

Learn how Prometheus native histograms improve API latency visibility and how to migrate gateway dashboards, alerts, and SLOs safely.

Learn how AISIX usage events and Prometheus metrics reveal MCP tool volume, latency, failures, limits, and guardrail blocks without storing sensitive payloads.

This tutorial walks you through setting up monitoring on a microservice application using Prometheus and Grafana.

Prometheus plugins often cause long tail requests, but APISIX can solve this problem and reduces the delay from 1s to 10ms.