chat/config.yaml

# Hanzo Router Configuration
# Hanzo LLM proxy -- unified LLM gateway routing all models through api.hanzo.ai

model_list:
  # =====================
  # Zen model family (Hanzo AI)
  # Publishable key (HANZO_API_KEY) for unauthenticated users.
  # Authenticated users override with their own key via IAM (hanzo.id).
  # =====================
  - model_name: zen3-nano
    litellm_params:
      model: openai/zen3-nano
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen3-nano: 4B dense, fast free-tier model"

  - model_name: zen4-mini
    litellm_params:
      model: openai/zen4-mini
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-mini: 8B dense, fast and efficient"

  - model_name: zen
    litellm_params:
      model: openai/zen
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen: 32B default general-purpose model"

  - model_name: zen4-pro
    litellm_params:
      model: openai/zen4-pro
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-pro: 80B MoE flagship reasoning"

  - model_name: zen4
    litellm_params:
      model: openai/zen4
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4: 744B MoE frontier model"

  - model_name: zen4-max
    litellm_params:
      model: openai/zen4-max
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-max: 1.04T MoE, 256K context"

  - model_name: zen4-ultra
    litellm_params:
      model: openai/zen4-ultra
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-ultra: 744B MoE + CoT reasoning"

  - model_name: zen4-thinking
    litellm_params:
      model: openai/zen4-thinking
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-thinking: 80B MoE with chain-of-thought"

  - model_name: zen4-coder-flash
    litellm_params:
      model: openai/zen4-coder-flash
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-coder-flash: 30B MoE, fast code specialist"

  - model_name: zen4-coder
    litellm_params:
      model: openai/zen4-coder
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-coder: 480B MoE code specialist"

  - model_name: zen4-coder-pro
    litellm_params:
      model: openai/zen4-coder-pro
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY
    model_info:
      description: "zen4-coder-pro: 480B dense BF16 coding model"

  # =====================
  # Third-party models (via Hanzo Cloud)
  # =====================
  - model_name: gpt-4o
    litellm_params:
      model: openai/gpt-4o
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY

  - model_name: gpt-4o-mini
    litellm_params:
      model: openai/gpt-4o-mini
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY

  - model_name: claude-sonnet-4-5
    litellm_params:
      model: openai/claude-sonnet-4-5
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY

  - model_name: claude-haiku-4-5
    litellm_params:
      model: openai/claude-haiku-4-5
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY

  # =====================
  # Wildcard passthrough
  # =====================
  - model_name: "openai/*"
    litellm_params:
      model: "openai/*"
      api_base: https://api.hanzo.ai/v1
      api_key: os.environ/HANZO_API_KEY

litellm_settings:
  drop_params: true
  num_retries: 3
  request_timeout: 300
  telemetry: false

router_settings:
  routing_strategy: simple-shuffle
  enable_pre_call_checks: true
  redis_host: os.environ/REDIS_HOST
  redis_password: os.environ/REDIS_PASSWORD
  redis_port: os.environ/REDIS_PORT

general_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
  store_model_in_db: true
  database_url: os.environ/DATABASE_URL
  database_connection_pool_limit: 10

  # UI Configuration
  ui_access_mode: "admin"
  ui_username: "admin"
  ui_password: "hanzo123"

  # Branding
  custom_branding:
    app_name: "Hanzo Router"
    logo_url: "/static/hanzo-logo.png"
    primary_color: "#000000"
    documentation_url: "https://docs.hanzo.ai"
    support_email: "support@hanzo.ai"

  # MCP Integration
  mcp_enabled: true
  mcp_servers:
    - name: "hanzo-mcp"
      command: ["python", "-m", "hanzo_mcp_server"]
    - name: "hanzo-code-executor"
      command: ["python", "/app/mcp/hanzo_code_executor.py"]
      env:
        RUNTIME_API_URL: os.environ/RUNTIME_API_URL
        RUNTIME_API_KEY: os.environ/RUNTIME_API_KEY

  # Runtime API Integration
  runtime_api_enabled: true
  runtime_api_url: os.environ/RUNTIME_API_URL
  runtime_api_key: os.environ/RUNTIME_API_KEY

# Enable health checks
health_check_interval: 30

# Runtime execution models (for code execution)
runtime_models:
  - model_name: "hanzo-runtime-python"
    description: "Execute Python code in secure sandboxes"
    runtime_language: "python"

  - model_name: "hanzo-runtime-typescript"
    description: "Execute TypeScript code in secure sandboxes"
    runtime_language: "typescript"