model_list:
  # ----- GROQ LLM MODELS -----
  - model_name: llama-3.1-8b
    litellm_params:
      model: groq/llama-3.1-8b-instant
      api_key: os.environ/GROQ_API_KEY

  - model_name: qwen-qwq-32b
    litellm_params:
      model: groq/qwen/qwen3-32b
      api_key: os.environ/GROQ_API_KEY

  # ----- Google AI Studio LLM MODELS -----
  - model_name: gemini-2.5-pro
    litellm_params:
      model: gemini/gemini-2.5-pro
      api_key: os.environ/GEMINI_API_KEY
      # Optimized for finding "needles" in 1,000+ page documents
      context_window: 2000000

  - model_name: gemini-2.5-flash
    litellm_params:
      model: gemini/gemini-2.5-flash
      api_key: os.environ/GEMINI_API_KEY
      drop_params: true
      rpm: 15

  # ----- CEREBRAS LLM MODELS -----
  
  - model_name: qwen3-235b
    litellm_params:
      model: cerebras/qwen-3-235b-a22b-instruct-2507
      api_key: os.environ/CEREBRAS_API_KEY
      api_base: https://api.cerebras.ai/v1

  # ----- OPENROUTER LLM MODELS -----
  - model_name: deepseek-r1
    litellm_params:
      model: openrouter/deepseek/deepseek-r1
      api_key: os.environ/OPENROUTER_API_KEY

  - model_name: gpt-oss-120b
    litellm_params:
      model: openrouter/openai/gpt-oss-120b
      api_key: os.environ/OPENROUTER_API_KEY

litellm_settings:
  drop_params: true
  request_timeout: 60
  num_retries: 2
  convert_input_to_str: true