# LiteLLM config for inference.coop
# MVP config: Tinfoil only (TEE-protected, privacy-first)
# Two models: DeepSeek V4 Flash (default, best agents) + GPT-OSS 120B (cheapest)
# Provider key set via environment variable or Admin UI

model_list:
  # DeepSeek V4 Flash — default model
  # Best agent performance (Terminal Bench 2.1: 82.7, DeepSWE: 54.4)
  # MoE, 1M context, tool calling, $0.30/$0.70 per M tokens
  - model_name: deepseek-v4-flash
    litellm_params:
      model: openai/deepseek-v4-flash
      api_base: https://api.tinfoil.sh/v1
      api_key: os.environ/TINFOIL_API_KEY

  # GPT-OSS 120B — lightweight fallback
  # Built for agentic workflows, web search + code execution
  # Apache 2.0, $0.15/$0.60 per M tokens
  - model_name: gpt-oss-120b
    litellm_params:
      model: openai/gpt-oss-120b
      api_base: https://api.tinfoil.sh/v1
      api_key: os.environ/TINFOIL_API_KEY

# Fallback: if DeepSeek is down, use GPT-OSS
router_settings:
  num_retries: 2
  timeout: 30
  fallbacks:
    - deepseek-v4-flash:
        - gpt-oss-120b

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

litellm_settings:
  salt_key: os.environ/LITELLM_SALT_KEY
  drop_params: true
  num_threads: 4
  request_timeout: 30