{
"title": "LangWatch AI Gateway",
"tags": ["langwatch", "ai-gateway", "llm"],
"timezone": "browser",
"schemaVersion": 39,
"version": 1,
"refresh": "30s",
"time": { "from": "now-1h", "to": "now" },
"templating": {
"list": [
{
"name": "datasource",
"type": "datasource",
"query": "prometheus",
"current": { "text": "Prometheus", "value": "Prometheus" }
},
{
"name": "namespace",
"type": "query",
"datasource": "$datasource",
"query": "label_values(gateway_http_requests_total, namespace)",
"current": { "text": "langwatch", "value": "langwatch" },
"includeAll": false
},
{
"name": "pod",
"type": "query",
"datasource": "$datasource",
"query": "label_values(gateway_http_requests_total{namespace=\"$namespace\"}, pod)",
"includeAll": true,
"multi": true
}
]
},
"panels": [
{
"type": "row",
"title": "Request health",
"gridPos": { "x": 0, "y": 0, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Request rate",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 1, "w": 8, "h": 7 },
"targets": [{
"expr": "sum by (status) (rate(gateway_http_requests_total{namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))",
"legendFormat": "{{status}}"
}],
"fieldConfig": { "defaults": { "unit": "reqps" } }
},
{
"type": "timeseries",
"title": "Latency (p50 / p95 / p99)",
"datasource": "$datasource",
"gridPos": { "x": 8, "y": 1, "w": 8, "h": 7 },
"targets": [
{ "expr": "histogram_quantile(0.50, sum by (le) (rate(gateway_http_request_duration_seconds_bucket{namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", "legendFormat": "p50" },
{ "expr": "histogram_quantile(0.95, sum by (le) (rate(gateway_http_request_duration_seconds_bucket{namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", "legendFormat": "p95" },
{ "expr": "histogram_quantile(0.99, sum by (le) (rate(gateway_http_request_duration_seconds_bucket{namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", "legendFormat": "p99" }
],
"fieldConfig": { "defaults": { "unit": "s" } }
},
{
"type": "stat",
"title": "5xx rate",
"datasource": "$datasource",
"gridPos": { "x": 16, "y": 1, "w": 8, "h": 7 },
"targets": [{
"expr": "sum(rate(gateway_http_requests_total{namespace=\"$namespace\", status=~\"5..\"}[$__rate_interval])) / sum(rate(gateway_http_requests_total{namespace=\"$namespace\"}[$__rate_interval]))"
}],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 0.01 },
{ "color": "red", "value": 0.05 }
]
}
}
}
},
{
"type": "row",
"title": "Provider health",
"gridPos": { "x": 0, "y": 8, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Circuit state by credential (0=closed 1=open 2=half-open)",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 9, "w": 12, "h": 7 },
"targets": [{
"expr": "gateway_circuit_state{namespace=\"$namespace\", pod=~\"$pod\"}",
"legendFormat": "{{credential_id}}"
}]
},
{
"type": "timeseries",
"title": "Upstream latency p95 by provider",
"datasource": "$datasource",
"gridPos": { "x": 12, "y": 9, "w": 12, "h": 7 },
"targets": [{
"expr": "histogram_quantile(0.95, sum by (provider, le) (rate(gateway_provider_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])))",
"legendFormat": "{{provider}}"
}],
"fieldConfig": { "defaults": { "unit": "s" } }
},
{
"type": "timeseries",
"title": "Fallback events per sec",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 16, "w": 24, "h": 6 },
"targets": [{
"expr": "sum by (from_credential, to_credential) (rate(gateway_fallback_events_total{namespace=\"$namespace\"}[$__rate_interval]))",
"legendFormat": "{{from_credential}} → {{to_credential}}"
}]
},
{
"type": "row",
"title": "Auth cache",
"gridPos": { "x": 0, "y": 22, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Auth cache hit rate",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 23, "w": 12, "h": 7 },
"targets": [
{ "expr": "sum(rate(gateway_auth_cache_hits_total{namespace=\"$namespace\", tier=\"l1\"}[$__rate_interval])) / sum(rate(gateway_auth_cache_lookups_total{namespace=\"$namespace\"}[$__rate_interval]))", "legendFormat": "hit rate" }
],
"fieldConfig": { "defaults": { "unit": "percentunit" } }
},
{
"type": "timeseries",
"title": "Resolve-key round-trips to control plane",
"datasource": "$datasource",
"gridPos": { "x": 12, "y": 23, "w": 12, "h": 7 },
"targets": [{
"expr": "sum(rate(gateway_control_plane_requests_total{namespace=\"$namespace\", endpoint=\"resolve-key\"}[$__rate_interval]))"
}],
"fieldConfig": { "defaults": { "unit": "reqps" } }
},
{
"type": "row",
"title": "Budgets",
"gridPos": { "x": 0, "y": 30, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Budget blocks by scope",
"description": "The gateway records spend and the control plane writes the ledger. This counter is the only gateway-side signal that a hard cap rejected traffic.",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 31, "w": 12, "h": 7 },
"targets": [{
"expr": "sum by (scope) (rate(gateway_budget_blocks_total{namespace=\"$namespace\"}[$__rate_interval]))",
"legendFormat": "{{scope}}"
}]
},
{
"type": "timeseries",
"title": "Spend records written and dropped",
"description": "Budget debits come from these records. A drop is spend that is never billed and never enforced against.",
"datasource": "$datasource",
"gridPos": { "x": 12, "y": 31, "w": 12, "h": 7 },
"targets": [
{ "expr": "sum(rate(gateway_spend_spool_appended_total{namespace=\"$namespace\"}[$__rate_interval]))", "legendFormat": "written" },
{ "expr": "sum by (reason) (rate(gateway_spend_spool_dropped_total{namespace=\"$namespace\"}[$__rate_interval]))", "legendFormat": "dropped / {{reason}}" }
],
"fieldConfig": { "defaults": { "unit": "reqps" } }
},
{
"type": "row",
"title": "Guardrails",
"gridPos": { "x": 0, "y": 38, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Verdicts by direction",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 39, "w": 12, "h": 7 },
"targets": [{
"expr": "sum by (direction, verdict) (rate(gateway_guardrail_verdicts_total{namespace=\"$namespace\"}[$__rate_interval]))",
"legendFormat": "{{direction}} / {{verdict}}"
}]
},
{
"type": "timeseries",
"title": "Blocks by direction",
"datasource": "$datasource",
"gridPos": { "x": 12, "y": 39, "w": 12, "h": 7 },
"targets": [{
"expr": "sum by (direction) (rate(gateway_guardrail_verdicts_total{namespace=\"$namespace\", verdict=\"block\"}[$__rate_interval]))",
"legendFormat": "{{direction}}"
}]
},
{
"type": "row",
"title": "Streaming",
"gridPos": { "x": 0, "y": 46, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Active streams",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 47, "w": 12, "h": 7 },
"targets": [{
"expr": "sum(gateway_streaming_active{namespace=\"$namespace\", pod=~\"$pod\"})"
}]
},
{
"type": "timeseries",
"title": "Guardrail fail-open rate",
"description": "Emitted on any direction when the control-plane guardrail call fails and the gateway lets the traffic through unchecked. Sustained > 0 means the evaluator is missing its SLO. The stream_chunk series is expected to be the noisy one, because that direction always fails open so a slow policy service never stalls a stream; treat it as the chunk-level enforcement gap. Use the langwatch.guardrail.stream_chunk_fail_open trace attribute to see why an individual bypass happened.",
"datasource": "$datasource",
"gridPos": { "x": 12, "y": 47, "w": 12, "h": 7 },
"targets": [{
"expr": "sum by (direction) (rate(gateway_guardrail_verdicts_total{namespace=\"$namespace\", verdict=\"fail_open\"}[$__rate_interval]))",
"legendFormat": "{{direction}}"
}]
},
{
"type": "row",
"title": "Prompt cache",
"gridPos": { "x": 0, "y": 54, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Prompt cache outcomes",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 55, "w": 24, "h": 7 },
"targets": [{
"expr": "sum by (outcome) (rate(gateway_cache_hits_total{namespace=\"$namespace\"}[$__rate_interval]))",
"legendFormat": "{{outcome}}"
}]
},
{
"type": "row",
"title": "Infrastructure",
"gridPos": { "x": 0, "y": 62, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Pod replicas ready",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 63, "w": 8, "h": 7 },
"targets": [{
"expr": "sum(kube_deployment_status_replicas_available{namespace=\"$namespace\", deployment=\"langwatch-gateway\"})"
}]
},
{
"type": "timeseries",
"title": "CPU + memory per pod",
"datasource": "$datasource",
"gridPos": { "x": 8, "y": 63, "w": 8, "h": 7 },
"targets": [
{ "expr": "sum by (pod) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=~\"langwatch-gateway-.*\"}[$__rate_interval]))", "legendFormat": "cpu / {{pod}}" },
{ "expr": "sum by (pod) (container_memory_working_set_bytes{namespace=\"$namespace\", pod=~\"langwatch-gateway-.*\"}) / 1024 / 1024", "legendFormat": "mem MB / {{pod}}" }
]
},
{
"type": "timeseries",
"title": "Goroutines per pod",
"description": "Monotonic climb = goroutine leak. See the AI Gateway troubleshooting page.",
"datasource": "$datasource",
"gridPos": { "x": 16, "y": 63, "w": 8, "h": 7 },
"targets": [{
"expr": "go_goroutines{namespace=\"$namespace\", pod=~\"langwatch-gateway-.*\"}",
"legendFormat": "{{pod}}"
}]
},
{
"type": "row",
"title": "Lifecycle (drain)",
"gridPos": { "x": 0, "y": 70, "w": 24, "h": 1 }
},
{
"type": "timeseries",
"title": "Draining pods",
"description": "gateway_draining flips to 1 on SIGTERM; a pod stuck at 1 for > terminationGracePeriodSeconds is a hung handler (see the AI Gateway troubleshooting page).",
"datasource": "$datasource",
"gridPos": { "x": 0, "y": 71, "w": 12, "h": 7 },
"targets": [{
"expr": "sum by (pod) (gateway_draining{namespace=\"$namespace\"})",
"legendFormat": "{{pod}}"
}]
},
{
"type": "timeseries",
"title": "In-flight requests",
"description": "Paired with Draining. A healthy drain curves to 0; flat while draining=1 means a handler is hung.",
"datasource": "$datasource",
"gridPos": { "x": 12, "y": 71, "w": 12, "h": 7 },
"targets": [{
"expr": "sum by (pod) (gateway_in_flight_requests{namespace=\"$namespace\"})",
"legendFormat": "{{pod}}"
}]
}
]
}
