model_list:
  - model_name: qwen3.8-27b-local
    litellm_params:
      # Static name — llama.cpp serves whatever model it loaded regardless of
      # what's requested here; this string isn't shell-expanded (this file
      # isn't docker-compose.yml, .env vars don't reach it).
      model: openai/qwen3.8-27b-local
      api_base: http://llama-server:8080/v1
      api_key: local
      # Qwen3 is a reasoning model — it spends output tokens on
      # reasoning_content before ever writing content. Callers that don't
      # set their own max_tokens (Open WebUI's default request didn't) hit
      # llama.cpp's low default, so the model runs out mid-thought and
      # content comes back empty. This is a floor, not a cap — any caller
      # that passes its own max_tokens still overrides it.
      max_tokens: 4096
    model_info:
      # Shadow cloud-cost estimate — priced against Claude Sonnet 5's published
      # rate, not real spend (this proxy only ever routes to the local model).
      # Source: https://platform.claude.com/docs/en/about-claude/pricing,
      # checked 2026-08-25. Update these two numbers if that page changes.
      input_cost_per_token: 0.000002   # $2 / MTok
      output_cost_per_token: 0.00001   # $10 / MTok

router_settings:
  # ponytail: LiteLLM's request-prioritization scheduler is beta (see
  # docs/proxy-request-priority.md) — exact settings key/shape must be
  # confirmed against LiteLLM's current docs and smoke-tested against
  # llama.cpp before workloads depend on it. Single-instance deployment,
  # no Redis configured — add one only if the scheduler turns out to need it.
  enable_priority_scheduling: true

general_settings:
  master_key: os.environ/LITELLM_MASTER_KEY