{
  "annotations": {
    "list": [
      {
        "builtIn": 1,
        "datasource": {
          "type": "grafana",
          "uid": "-- Grafana --"
        },
        "enable": true,
        "hide": true,
        "iconColor": "rgba(0, 211, 255, 1)",
        "name": "Annotations & Alerts",
        "target": {
          "limit": 100,
          "matchAny": false,
          "tags": [],
          "type": "dashboard"
        },
        "type": "dashboard"
      }
    ]
  },
  "editable": true,
  "fiscalYearStartMonth": 0,
  "graphTooltip": 1,
  "links": [],
  "liveNow": false,
  "panels": [
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "mappings": [
            {
              "options": {
                "0": {
                  "color": "red",
                  "index": 1,
                  "text": "down"
                },
                "1": {
                  "color": "green",
                  "index": 0,
                  "text": "up"
                }
              },
              "type": "value"
            }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "red",
                "value": null
              },
              {
                "color": "green",
                "value": 1
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 6,
        "x": 0,
        "y": 0
      },
      "id": 1,
      "options": {
        "colorMode": "background",
        "graphMode": "none",
        "justifyMode": "center",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "11.0.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "up{job=\"litellm\", instance=~\"$instance\"}",
          "legendFormat": "{{instance}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Scrape status",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "decimals": 3,
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 6,
        "x": 6,
        "y": 0
      },
      "id": 2,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "11.0.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "sum(rate(litellm_proxy_total_requests_metric_total{job=\"litellm\", instance=~\"$instance\"}[$__rate_interval]))",
          "legendFormat": "requests/s",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Proxy request rate",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "decimals": 3,
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 6,
        "x": 12,
        "y": 0
      },
      "id": 3,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "11.0.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "sum(rate(litellm_proxy_failed_requests_metric_total{job=\"litellm\", instance=~\"$instance\"}[$__rate_interval])) or vector(0)",
          "legendFormat": "errors/s",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Proxy error rate",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "decimals": 2,
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 6,
        "x": 18,
        "y": 0
      },
      "id": 4,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "11.0.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "histogram_quantile(0.95, sum(rate(litellm_request_total_latency_metric_bucket{job=\"litellm\", instance=~\"$instance\"}[$__rate_interval])) by (le))",
          "legendFormat": "p95",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "p95 total latency",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "fillOpacity": 10,
            "lineInterpolation": "linear",
            "lineWidth": 2,
            "showPoints": "never",
            "spanNulls": false
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 4
      },
      "id": 5,
      "options": {
        "legend": {
          "calcs": [
            "lastNotNull"
          ],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "sum by (requested_model) (rate(litellm_proxy_total_requests_metric_total{job=\"litellm\", instance=~\"$instance\"}[$__rate_interval]))",
          "legendFormat": "{{requested_model}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Requests by requested model",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "fillOpacity": 10,
            "lineInterpolation": "linear",
            "lineWidth": 2,
            "showPoints": "never",
            "spanNulls": false
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 4
      },
      "id": 6,
      "options": {
        "legend": {
          "calcs": [
            "lastNotNull"
          ],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "sum by (model) (rate(litellm_total_tokens_metric_total{job=\"litellm\", instance=~\"$instance\"}[$__rate_interval]))",
          "legendFormat": "{{model}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Token rate by model",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "unit": "currencyUSD"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 12
      },
      "id": 7,
      "options": {
        "displayMode": "gradient",
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": false
        },
        "orientation": "horizontal",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": true
        },
        "showUnfilled": true,
        "valueMode": "color"
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "topk(10, sum by (model) (increase(litellm_spend_metric_total{job=\"litellm\", instance=~\"$instance\"}[$__range])))",
          "legendFormat": "{{model}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Spend by model in selected range",
      "type": "bargauge"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "fillOpacity": 10,
            "lineInterpolation": "linear",
            "lineWidth": 2,
            "showPoints": "never",
            "spanNulls": false
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 12
      },
      "id": 8,
      "options": {
        "legend": {
          "calcs": [
            "lastNotNull"
          ],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "single",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "editorMode": "code",
          "expr": "histogram_quantile(0.95, sum by (le, model) (rate(litellm_llm_api_latency_metric_bucket{job=\"litellm\", instance=~\"$instance\"}[$__rate_interval])))",
          "legendFormat": "{{model}} p95",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "LLM API latency by model",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "loki",
        "uid": "loki"
      },
      "gridPos": {
        "h": 10,
        "w": 24,
        "x": 0,
        "y": 20
      },
      "id": 9,
      "options": {
        "dedupStrategy": "none",
        "enableLogDetails": true,
        "prettifyLogMessage": false,
        "showCommonLabels": false,
        "showLabels": false,
        "showTime": true,
        "sortOrder": "Descending",
        "wrapLogMessage": true
      },
      "targets": [
        {
          "datasource": {
            "type": "loki",
            "uid": "loki"
          },
          "editorMode": "code",
          "expr": "{host=\"AZ-CLD-1\", unit=~\"podman-litellm.service|docker-litellm.service|litellm.service\"}",
          "queryType": "range",
          "refId": "A"
        }
      ],
      "title": "LiteLLM logs from Loki",
      "type": "logs"
    }
  ],
  "refresh": "30s",
  "schemaVersion": 39,
  "style": "dark",
  "tags": [
    "az",
    "litellm",
    "prometheus",
    "loki",
    "provisioned"
  ],
  "templating": {
    "list": [
      {
        "current": {
          "selected": true,
          "text": "All",
          "value": "$__all"
        },
        "datasource": {
          "type": "prometheus",
          "uid": "prometheus"
        },
        "definition": "label_values(up{job=\"litellm\"}, instance)",
        "hide": 0,
        "includeAll": true,
        "label": "Instance",
        "multi": true,
        "name": "instance",
        "options": [],
        "query": {
          "query": "label_values(up{job=\"litellm\"}, instance)",
          "refId": "PrometheusVariableQueryEditor-VariableQuery"
        },
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "sort": 1,
        "type": "query"
      }
    ]
  },
  "time": {
    "from": "now-6h",
    "to": "now"
  },
  "timepicker": {},
  "timezone": "browser",
  "title": "AZ LiteLLM Observability",
  "uid": "az-litellm-observability",
  "version": 1,
  "weekStart": ""
}