---
name: llm-route-by-model
telemetry:
  metrics:
    - llm.interactions
  exporters:
    prometheus_exporter:
      type: prometheus
      options:
        endpoints:
          - scheme: http
            port: 7190
            path: /metrics
guards:
  api_key:
    type: inline
bindings:
  north_tcp_server:
    type: tcp
    kind: server
    options:
      host: 0.0.0.0
      port: 7161
    exit: north_http_server
  north_http_server:
    type: http
    kind: server
    exit: north_llm_server
  north_llm_server:
    type: llm
    kind: server
    options:
      dialect: openai
      authorization:
        api_key:
          credentials: "Bearer {credentials}"
    exit: north_llm_proxy
  #region llm_proxy
  north_llm_proxy:
    type: llm
    kind: proxy
    routes:
      - when:
          - model:
              - gpt-4o-mini
        exit: south_llm_client_mini
      - when:
          - model:
              - gpt-*
        exit: south_llm_client_openai
  #endregion llm_proxy
  #region llm_clients
  south_llm_client_mini:
    type: llm
    kind: client
    options:
      dialect: openai
      server: https://api.openai.com
      authorization:
        api_key:
          credentials: "Bearer {credentials}"
    telemetry:
      metrics:
        - llm.*
    exit: sys:http_client
  south_llm_client_openai:
    type: llm
    kind: client
    options:
      dialect: openai
      server: https://api.openai.com
      authorization:
        api_key:
          credentials: "Bearer {credentials}"
    telemetry:
      metrics:
        - llm.*
    exit: sys:http_client
  #endregion llm_clients