diff --git a/k8s/infra/monitoring/alerts/api-gateway-alerts.yaml b/k8s/infra/monitoring/alerts/api-gateway-alerts.yaml
new file mode 100644
index 0000000..49e904b
--- /dev/null
+++ b/k8s/infra/monitoring/alerts/api-gateway-alerts.yaml
@@ -0,0 +1,160 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: api-gateway-alerts
+  namespace: monitoring
+  labels:
+    release: prometheus
+spec:
+  groups:
+    # ================================================================
+    # SLA Targets (based on canary traffic baselines):
+    #
+    # Availability:  99.9% (43.8 min downtime/month)
+    # LLM Chat:      p95 < 1s (qwen), p95 < 2s (reasoning), p95 < 5s (ornith)
+    # Embeddings:    p95 < 500ms
+    # Rerank:        p95 < 500ms
+    # Models list:   p95 < 300ms
+    # Error rate:    < 1% (5xx), < 5% (4xx excluding auth)
+    #
+    # Baselines from 200-request canary run:
+    #   qwen p99=609ms, reasoning p99=328ms, embeddings p99=287ms,
+    #   rerank p99=218ms, models p99=277ms
+    # SLA set at ~2x p99 for headroom.
+    # ================================================================
+
+    - name: api-gateway.availability
+      rules:
+        # Gateway pods not ready
+        - alert: APIGatewayDown
+          expr: sum(kube_pod_status_ready{namespace="api",condition="true"}) == 0
+          for: 1m
+          labels:
+            severity: critical
+          annotations:
+            summary: "API Gateway has zero ready pods"
+
+        # Gateway pod count below desired
+        - alert: APIGatewayDegraded
+          expr: |
+            sum(kube_pod_status_ready{namespace="api",condition="true"})
+            < kube_deployment_spec_replicas{namespace="api",deployment="api-gateway"}
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "API Gateway {{ $value }} ready pods below desired replica count"
+
+        # Blackbox probe down
+        - alert: APIGatewayProbeDown
+          expr: probe_success{instance=~".*api.riotpiao.com.*"} == 0
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: "API Gateway probe failed: {{ $labels.instance }}"
+
+        # LLM serving pods not ready
+        - alert: LLMServingDown
+          expr: sum(kube_pod_status_ready{namespace="llm-serving",condition="true"}) == 0
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: "All LLM serving pods down"
+
+        # Individual predictor down
+        - alert: LLMPredictorDown
+          expr: |
+            kube_deployment_status_replicas_ready{namespace="llm-serving"}
+            < kube_deployment_spec_replicas{namespace="llm-serving"}
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $labels.deployment }} has {{ $value }} ready (below desired)"
+
+    - name: api-gateway.latency
+      # SLA: latency thresholds at ~2x measured p99
+      rules:
+        # Ingress-level latency (all requests through nginx)
+        - alert: APIGatewayLatencyHigh
+          expr: |
+            histogram_quantile(0.95,
+              sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress="api"}[5m])) by (le)
+            ) > 2
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "API Gateway p95 latency {{ $value | printf \"%.1f\" }}s (SLA: <2s)"
+
+        # Extreme latency (p99 > 5s)
+        - alert: APIGatewayLatencyCritical
+          expr: |
+            histogram_quantile(0.99,
+              sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress="api"}[5m])) by (le)
+            ) > 5
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "API Gateway p99 latency {{ $value | printf \"%.1f\" }}s (SLA: <5s)"
+
+    - name: api-gateway.errors
+      rules:
+        # 5xx error rate > 1%
+        - alert: APIGateway5xxErrorRate
+          expr: |
+            sum(rate(nginx_ingress_controller_requests{ingress="api",status=~"5.."}[5m]))
+            / sum(rate(nginx_ingress_controller_requests{ingress="api"}[5m]))
+            > 0.01
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "API Gateway 5xx rate {{ $value | humanizePercentage }} (SLA: <1%)"
+
+        # Total error rate > 10% (including 4xx)
+        - alert: APIGatewayHighErrorRate
+          expr: |
+            sum(rate(nginx_ingress_controller_requests{ingress="api",status=~"[45].."}[5m]))
+            / sum(rate(nginx_ingress_controller_requests{ingress="api"}[5m]))
+            > 0.10
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "API Gateway total error rate {{ $value | humanizePercentage }} (SLA: <10%)"
+
+    - name: api-gateway.resources
+      rules:
+        # Gateway pod restart
+        - alert: APIGatewayRestarted
+          expr: increase(kube_pod_container_status_restarts_total{namespace="api"}[15m]) > 0
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "API Gateway pod {{ $labels.pod }} restarted"
+
+        # LLM predictor restart
+        - alert: LLMPredictorRestarted
+          expr: increase(kube_pod_container_status_restarts_total{namespace="llm-serving"}[15m]) > 0
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "LLM predictor {{ $labels.pod }} restarted"
+
+        # Gateway high memory (>80% of limit)
+        - alert: APIGatewayHighMemory
+          expr: |
+            sum(container_memory_working_set_bytes{namespace="api",container="gateway"}) by (pod)
+            / sum(kube_pod_container_resource_limits{namespace="api",container="gateway",resource="memory"}) by (pod)
+            > 0.8
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Gateway pod {{ $labels.pod }} memory at {{ $value | humanizePercentage }} of limit"
diff --git a/k8s/infra/monitoring/alerts/cluster-alerts.yaml b/k8s/infra/monitoring/alerts/cluster-alerts.yaml
new file mode 100644
index 0000000..040055b
--- /dev/null
+++ b/k8s/infra/monitoring/alerts/cluster-alerts.yaml
@@ -0,0 +1,177 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: cluster-alerts
+  namespace: monitoring
+  labels:
+    release: prometheus
+spec:
+  groups:
+    - name: cluster.availability
+      rules:
+        # Node down
+        - alert: NodeNotReady
+          expr: kube_node_status_condition{condition="Ready",status="true"} == 0
+          for: 2m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Node {{ $labels.node }} is NotReady"
+
+        # Pod stuck pending (scheduling failure)
+        - alert: PodStuckPending
+          expr: sum(kube_pod_status_phase{phase="Pending"}) > 0
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $value }} pod(s) stuck in Pending state for >10m"
+
+        # CrashLoopBackOff
+        - alert: PodCrashLooping
+          expr: sum(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff"}) by (namespace, pod) > 0
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.pod }} in CrashLoopBackOff"
+
+        # OOMKilled spike
+        - alert: OOMKilledSpike
+          expr: sum(increase(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[1h])) > 3
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $value }} OOMKilled events in last hour"
+
+        # Deployment replicas unavailable
+        - alert: DeploymentReplicasUnavailable
+          expr: kube_deployment_status_replicas_unavailable > 0
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.deployment }} has {{ $value }} unavailable replicas"
+
+    - name: cluster.jobs
+      rules:
+        # Job failed
+        - alert: JobFailed
+          expr: kube_job_status_failed > 0
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed"
+
+        # Job stuck running >2h
+        - alert: JobStuckRunning
+          expr: |
+            kube_job_status_active == 1
+            and on(job_name,namespace)
+            (time() - kube_job_status_start_time) > 7200
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Job {{ $labels.namespace }}/{{ $labels.job_name }} running >2h"
+
+        # CronJob missed schedule
+        - alert: CronJobMissedSchedule
+          expr: |
+            (time() - kube_cronjob_status_last_schedule_time) > 2 * (kube_cronjob_spec_next_schedule_time - kube_cronjob_status_last_schedule_time)
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} missed schedule"
+
+    - name: cluster.resources
+      rules:
+        # Node CPU >90% sustained
+        - alert: NodeHighCPU
+          expr: (1 - avg(rate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance)) * 100 > 90
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Node {{ $labels.instance }} CPU at {{ $value | printf \"%.0f\" }}%"
+
+        # Node memory >90% sustained
+        - alert: NodeHighMemory
+          expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 90
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Node {{ $labels.instance }} memory at {{ $value | printf \"%.0f\" }}%"
+
+        # Node disk >85%
+        - alert: NodeDiskFull
+          expr: (1 - node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 > 85
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Node {{ $labels.instance }} disk at {{ $value | printf \"%.0f\" }}%"
+
+        # Container restart storm (>5 restarts in 15m)
+        - alert: ContainerRestartStorm
+          expr: sum(increase(kube_pod_container_status_restarts_total[15m])) by (namespace, pod) > 5
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.pod }} restarted {{ $value | printf \"%.0f\" }} times in 15m"
+
+    - name: cluster.storage
+      rules:
+        # Longhorn drive offline
+        - alert: LonghornDriveOffline
+          expr: longhorn_disk_health != 1
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Longhorn disk {{ $labels.node }} unhealthy"
+
+    - name: cluster.dns
+      rules:
+        # CoreDNS errors spike
+        - alert: CoreDNSErrorSpike
+          expr: sum(rate(coredns_dns_responses_total{rcode=~"SERVFAIL"}[5m])) > 0.5
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "CoreDNS SERVFAIL rate {{ $value | printf \"%.2f\" }}/s"
+
+    - name: cluster.probes
+      rules:
+        # Any blackbox probe down
+        - alert: ServiceProbeDown
+          expr: probe_success == 0
+          for: 3m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Probe failed: {{ $labels.instance }}"
+
+        # Probe latency >2s
+        - alert: ServiceProbeSlow
+          expr: probe_duration_seconds > 2
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Probe slow ({{ $value | printf \"%.1f\" }}s): {{ $labels.instance }}"
+
+        # Certificate expiry <14 days
+        - alert: CertificateExpiringSoon
+          expr: (certmanager_certificate_expiration_timestamp_seconds - time()) / 86400 < 14
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Certificate {{ $labels.name }} expires in {{ $value | printf \"%.0f\" }} days"
diff --git a/k8s/infra/monitoring/kustomization.yaml b/k8s/infra/monitoring/kustomization.yaml
index 0dffaad..549ee07 100644
--- a/k8s/infra/monitoring/kustomization.yaml
+++ b/k8s/infra/monitoring/kustomization.yaml
@@ -12,6 +12,8 @@ resources:
   - alerts/svc-grafana-rules.yaml
   - alerts/svc-minio-rules.yaml
   - alerts/svc-vault-rules.yaml
+  - alerts/cluster-alerts.yaml
+  - alerts/api-gateway-alerts.yaml
   - servicemonitors/argocd.yaml
   - servicemonitors/authentik.yaml
   - servicemonitors/forgejo.yaml