composes/litellm/config.yaml

model_list:
  - model_name: kimi-k3-free
    litellm_params:
      model: openai/moonshotai/kimi-k3-free
      api_base: https://api.tokenrouter.com/v1
      api_key: os.environ/TOKENROUTER_API_KEY

  - model_name: glm-5.3-flash-free
    litellm_params:
      model: openai/z-ai/glm-5.3-flash-free
      api_base: https://api.orcarouter.ai/v1
      api_key: os.environ/ORCAROUTER_API_KEY

  - model_name: kimi-for-coding
    litellm_params:
      model: anthropic/kimi-for-coding
      api_base: https://api.kimi.com/coding
      api_key: os.environ/KIMI_API_KEY

  - model_name: MiniMax-M3
    litellm_params:
      model: minimax/MiniMax-M3
      api_key: os.environ/MINIMAX_API_KEY

  - model_name: gemma-4-31b-it:free
    litellm_params:
      model: openrouter/google/gemma-4-31b-it:free
      api_key: os.environ/OPENROUTER_API_KEY

  - model_name: openrouter-free
    litellm_params:
      model: openrouter/openrouter/free
      api_key: os.environ/OPENROUTER_API_KEY

  - model_name: orcarouter-free
    litellm_params:
      model: openai/orcarouter/free
      api_base: https://api.orcarouter.ai/v1
      api_key: os.environ/ORCAROUTER_API_KEY

  - model_name: kilo-free
    litellm_params:
      model: openai/kilo-auto/free
      api_base: https://api.kilo.ai/api/gateway
      api_key: os.environ/KILO_API_KEY

  - model_name: deepseek-v4-flash-free
    litellm_params:
      model: openai/deepseek-v4-flash-free
      api_base: https://opencode.ai/zen/v1
      api_key: os.environ/OPENCODE_API_KEY

  - model_name: glm4.7
    litellm_params:
      model: nvidia_nim/z-ai/glm4.7
      api_key: os.environ/NVIDIA_NIM_API_KEY

  - model_name: gemini-embedding-001
    litellm_params:
      model: gemini/gemini-embedding-001
      api_key: os.environ/GEMINI_API_KEY
      dimensions: 1536

  - model_name: gemini-2.5-flash
    litellm_params:
      model: gemini/gemini-2.5-flash
      api_key: os.environ/GEMINI_API_KEY

  - model_name: gemma-4-31b-it
    litellm_params:
      model: gemini/gemma-4-31b-it
      api_key: os.environ/GEMINI_API_KEY

  - model_name: gemma-4-26b-a4b-it
    litellm_params:
      model: gemini/gemma-4-26b-a4b-it
      api_key: os.environ/GEMINI_API_KEY

  # - model_name: gemini/*
  #   litellm_params:
  #     model: gemini/*
  #     api_key: os.environ/GEMINI_API_KEY

  - model_name: gemma4:31b-cloud
    litellm_params:
      model: ollama/gemma4:31b-cloud
      api_base: https://ollama.com
      api_key: os.environ/OLLAMA_API_KEY

  # - model_name: glm-4.7-flash
  #   litellm_params:
  #     model: cloudflare/@cf/zai-org/glm-4.7-flash
  #     api_key: os.environ/CLOUDFLARE_API_KEY
  #     account_id: os.environ/CLOUDFLARE_ACCOUNT_ID

  # - model_name: deepseek-v4-pro
  #   litellm_params:
  #     model: openai/deepseek-v4-pro
  #     api_base: https://opencode.ai/zen/go/v1
  #     api_key: os.environ/OPENCODE_API_KEY

  # - model_name: qwen3.7-max
  #   litellm_params:
  #     model: anthropic/qwen3.7-max
  #     api_base: https://opencode.ai/zen/go/v1
  #     api_key: os.environ/OPENCODE_API_KEY

general_settings:
  proxy_batch_write_at: 60
  store_model_in_db: true
  store_prompts_in_spend_logs: false

router_settings:
  model_group_alias:
    claude: openrouter-free
    sonnet: openrouter-free
    opus: openrouter-free
    haiku: openrouter-free
    opencode: openrouter-free
    goclaw: openrouter-free
    openclaw: openrouter-free
    hermes: openrouter-free
  redis_host: os.environ/REDIS_HOST
  redis_port: os.environ/REDIS_PORT
  redis_password: os.environ/REDIS_PASSWORD
  enable_pre_call_check: true

litellm_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
  check_provider_endpoint: true
  set_verbose: false
  json_logs: true
  log_raw_request_response: false
  # turn_off_message_logging: false
  # redact_user_api_key_info: false
  service_callback: ["prometheus_system"]
  drop_params: true
  # max_budget: 100
  # budget_duration: 30d
  num_retries: 1
  request_timeout: 120
  telemetry: false
  cache: true
  cache_params:
    type: redis
    host: os.environ/REDIS_HOST
    port: os.environ/REDIS_PORT
    password: os.environ/REDIS_PASSWORD
    namespace: "litellm_cache"
    ttl: 600
  success_callback:
    # - "langfuse"
    - "prometheus"
  failure_callback:
    # - "langfuse"
    - "prometheus"