litellm/helm/litellm/values.yaml

# LiteLLM helm chart values

nameOverride: ""
fullnameOverride: ""

imagePullSecrets: []

# Optional Ingress wiring the three component Services behind a single L7
# entrypoint. Required when serving the static UI bundle over the network.
ingress:
  enabled: false
  className: ""
  annotations: {}
  host: ""        # optional; if set, becomes the rule's host
  tls: []

# Shared ServiceAccount used by all three component Deployments. Set
# `create: true` to have the chart provision it (e.g. when wiring an EKS
# Pod Identity association by SA name). Set `name` to use an existing SA
# (chart-created or out-of-band). When both are empty / false, pods run
# with the namespace's `default` SA.
serviceAccount:
  create: false
  automount: true
  annotations: {}
  name: ""

# Pre-install / pre-upgrade Helm hook that runs `prisma migrate deploy`
# against the writer database, creating the LiteLLM schema (tables that
# gateway + backend assume exist at startup: LiteLLM_Config,
# LiteLLM_VerificationToken, LiteLLM_SpendLogs, ...). Disable if your
# pipeline runs migrations out-of-band.
#
# Uses a dedicated `litellm-migrations` image (prisma CLI + the migration
# files from `litellm-proxy-extras`) instead of the backend image, so the
# Job doesn't drag in the rest of the proxy and doesn't run `prisma
# generate` — the migration engine doesn't need the generated client.
migrationJob:
  enabled: true
  backoffLimit: 4
  ttlSecondsAfterFinished: 120
  resources: {}
  image:
    repository: ghcr.io/berriai/litellm-migrations
    tag: ""              # defaults to .Chart.AppVersion
    pullPolicy: IfNotPresent
  # Extra env appended to the migration container. The migration entrypoint
  # uses the v2 resolver by default (no diff-and-force recovery — avoids the
  # schema thrashing seen during rolling deploys). To opt back into the v1
  # resolver, append `- name: USE_V2_MIGRATION_RESOLVER` / `value: "false"`.
  extraEnv: []

# Required: a master key used by gateway + backend to mint/verify proxy tokens.
# Must reference an existing Secret.
masterKey:
  secretName: litellm-master-key-secret              # name of a Secret containing the master key
  secretKey: master-key

# External Postgres connection. 
database:
  writer:
    host: ""
    port: 5432
    dbname: ""
    schema: ""
    useIAMAuth: false
    passwordSecret:
      name: litellm-writer-secret
      usernameKey: username
      passwordKey: password

  # Optional read-replica routing. When `reader.host` is set, the proxy routes
  # reads (find_*, count, group_by, query_raw/_first) to this endpoint while
  # writes stay on the writer. Leave `reader.host` empty to disable.
  reader:
    host: ""
    port: 5432
    dbname: ""
    schema: ""
    useIAMAuth: false
    passwordSecret:
      name: litellm-reader-secret
      usernameKey: username
      passwordKey: password

# Optional Redis (caching, rate limiting). Leave host empty to disable.
#
# Set `cluster: true` for Redis Cluster mode (e.g. AWS ElastiCache Cluster,
# self-hosted Redis Cluster). The chart emits REDIS_CLUSTER_NODES from
# `host` / `port` as the single seed; the cluster client discovers the
# remaining nodes from CLUSTER SLOTS at startup.
redis:
  cluster: false
  host: ""
  port: 6379
  passwordSecret:
    name: "" # Leave empty for auth-less Redis
    passwordKey: password

# ---------- gateway (LLM data plane) ----------
gateway:
  enabled: true
  logLevel: INFO
  # Number of uvicorn worker processes per gateway pod. Sets NUM_WORKERS,
  # consumed by the gateway image entrypoint. Default is 1.
  numWorkers: 1
  extraEnv: [] # Add extra environment variables to the gateway
  envConfigMaps: [] # Add extra environment variables to the gateway from config maps
  envSecrets: [] # Add extra environment variables to the gateway from secrets
  config:
    create: true
    proxy_config: {}
  image:
    repository: ghcr.io/berriai/litellm-gateway
    tag: ""              # defaults to .Chart.AppVersion
    pullPolicy: IfNotPresent
  service:
    type: ClusterIP
    port: 4000
  resources:
    requests:
      cpu: "1"
      memory: 4Gi
    limits:
      cpu: "2"
      memory: 4Gi
  livenessProbe:
    httpGet: { path: /health/liveliness, port: http }
    initialDelaySeconds: 10
    periodSeconds: 15
  readinessProbe:
    httpGet: { path: /health/readiness, port: http }
    initialDelaySeconds: 5
    periodSeconds: 10
  hpa:
    enabled: true
    minReplicas: 1
    maxReplicas: 10
    targetCPUUtilizationPercentage: 70
    targetMemoryUtilizationPercentage: 80
  podAnnotations: {}
  nodeSelector: {}
  tolerations: []
  affinity: {}

# ---------- backend (UI / management API) ----------
backend:
  enabled: true
  logLevel: INFO
  extraEnv: []
  envConfigMaps: []
  envSecrets: []
  image:
    repository: ghcr.io/berriai/litellm-backend
    tag: ""
    pullPolicy: IfNotPresent
  service:
    type: ClusterIP
    port: 4001
  resources:
    requests:
      cpu: "1"
      memory: 4Gi
    limits:
      cpu: "2"
      memory: 4Gi
  livenessProbe:
    httpGet: { path: /health/liveliness, port: http }
    initialDelaySeconds: 10
    periodSeconds: 15
  readinessProbe:
    httpGet: { path: /health/readiness, port: http }
    initialDelaySeconds: 5
    periodSeconds: 10
  hpa:
    enabled: true
    minReplicas: 1
    maxReplicas: 4
    targetCPUUtilizationPercentage: 70
  podAnnotations: {}
  nodeSelector: {}
  tolerations: []
  affinity: {}

# ---------- ui (Next.js static dashboard) ----------
ui:
  enabled: true
  logLevel: INFO
  extraEnv: []
  envConfigMaps: []
  envSecrets: []
  image:
    repository: ghcr.io/berriai/litellm-ui
    tag: ""
    pullPolicy: IfNotPresent
  service:
    type: ClusterIP
    port: 3000
  # The dashboard expects to know where to reach the backend API. Set this to
  # the externally-routable URL (typically the ingress host + /api or similar).
  backendUrl: ""
  resources:
    requests:
      cpu: 500m
      memory: 500Mi
    limits:
      cpu: "1"
      memory: 1Gi
  livenessProbe:
    httpGet: { path: /, port: http }
    initialDelaySeconds: 5
    periodSeconds: 20
  readinessProbe:
    httpGet: { path: /, port: http }
    initialDelaySeconds: 2
    periodSeconds: 10
  hpa:
    enabled: false
    minReplicas: 1
    maxReplicas: 3
    targetCPUUtilizationPercentage: 80
  podAnnotations: {}
  nodeSelector: {}
  tolerations: []
  affinity: {}