Keep the AI bill in check, tenant by tenant.

# What inference costs, and what happens when a backend fails: prices declared per backend, a
# monthly budget in euros per tenant beside the token budget, a soft cap that warns and moves the
# call to a cheaper backend, and fallbacks tried in order before any byte reaches the client - never
# an external one for a sensitive request.
version: 1
auth:
  issuers:
    - name: customers
      discovery: https://login.example.net/.well-known/openid-configuration
      audience: api
      tenant_claim: org
ai:
  security:
    - oidc: { scopes: [inference] }
  sensitive_header: X-Sensitive
  default_backend: eu-large
  sensitive_backend: on-prem
  backends:
    eu-large:
      url: https://api.provider.example/v1
      api_key: "file:/etc/flexway/secrets/provider-key"
      default_model: mistral-large
      external: true
      price: { input_per_mtok: 2.00, output_per_mtok: 6.00 }   # euros per million tokens
      fallback: [eu-small, on-prem]              # in order, on connection failure, 5xx, timeout
    eu-small:
      url: https://api.provider.example/v1
      api_key: "file:/etc/flexway/secrets/provider-key"
      default_model: mistral-small
      external: true
      price: { input_per_mtok: 0.10, output_per_mtok: 0.30 }
      fallback: [on-prem]
    on-prem:
      url: http://vllm.inference.svc:8000/v1
      default_model: mistral-7b-instruct
      price: { input_per_mtok: 0, output_per_mtok: 0 }      # 0 is a price: internal
  budget:
    store: "${COUNTERS_URL}"
    monthly_tokens: 40000000                     # both budgets hold: the first reached decides
    monthly_eur: 50                              # per tenant, over the calendar month
    soft: { at: 0.8, backend: eu-small }         # past 80 %: Flexway-Budget: soft, moved to eu-small
  overrides:
    - { match: { tenant: acme }, monthly_eur: 500 }