litellm-config.example.yaml

model_list:
  # Fast tier — quick, low-cost reasoning. Used for triage, mention parsing,
  # short chat replies, and any agent step that doesn't need a frontier model.
  - model_name: fast
    litellm_params:
      model: openai/gpt-4.1-mini
      api_key: os.environ/OPENAI_API_KEY
      max_tokens: 4096

  # Strong tier — complex reasoning, full code reviews, security triage.
  - model_name: strong
    litellm_params:
      model: openrouter/anthropic/claude-sonnet-4
      api_key: os.environ/OPENROUTER_API_KEY
      max_tokens: 8192

  # Code tier — code-focused tasks (diff review, code generation in flows).
  # Qwen3.5-35B-A3B is a Mixture-of-Experts coder model served via OpenRouter.
  - model_name: code
    litellm_params:
      model: openrouter/qwen/qwen3.5-35b-a3b
      api_key: os.environ/OPENROUTER_API_KEY
      max_tokens: 8192

router_settings:
  num_retries: 2

general_settings:
  master_key: sk-codeward-master-key