Route Telemetry — ML Junction docs

Metric · Definition
throughput_tps · Median output tokens per second over successful metered attempts in the trailing 30 days
latency_p50_ms · Median successful request latency in the trailing 30 days
latency_p95_ms · 95th percentile successful request latency
latency_p99_ms · 99th percentile successful request latency
uptime_30d · Successes divided by successes plus availability-impacting failures

Quality failures such as structured-output validation do not reduce uptime. They remain visible as quality_failures and in error series. This prevents a provider that is reachable but produced invalid output from being mislabeled as offline.

Sort by uptime descending for the default health-first route table.. Place routes without uptime after measured routes.. Use input price as the second sort key and priority as the final tie-breaker.. Hide a missing metric instead of rendering zero throughput, zero latency, or zero uptime.. Label percentiles explicitly; p50, p95, and p99 answer different user questions.

Canonical URL: https://mljunction.com/docs/route-telemetry