##yaml锚点方便配置。手动设定价格，方便ui中查看
x-definitions: &token_pricing
  input_cost_per_token: 1
  output_cost_per_token: 1

model_list:
  # ======================= 监控模型维护入口 =======================
  # 1. 这里的火山模型条目，就是“纳入监控模型”的主入口。
  # 2. 常规版本号模型（如 xxx-260215）会由 volc_limit_sync.py 自动推导成监控别名 xxx。
  # 3. 只有“资源包名与上游模型名不一致”或“一包多模型”时，才需要再改
  #    volc_limit_sync.py 里的 MANUAL_MONITORED_MODEL_ALIASES。
  # 4. 改完后运行 `python generate_keys.py`，检查监控别名和 HARD_DAILY_LIMITS 的限额来源。


          
 #=======================火山平台，限时免费 



### 


  #日常使用ds v3.2  ，强制think  
  - model_name: deepseek-v3.2
    litellm_params:
      <<: *token_pricing
      model: volcengine/deepseek-v3-2-251201
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY 
      # 说明中建议设置30分钟(1800秒)以上，避免深度思考过程中断连接
      timeout: 1800       
      # 关键配置2：启用思考模式
      # extra_body 中的参数会被直接合并到请求的 JSON body 中
      extra_headers:
        Connection: "close"
      extra_body:
        thinking:
          type: "enabled"
          
  - model_name: deepseek-v3.2-nothink
    litellm_params:
      <<: *token_pricing
      model: volcengine/deepseek-v3-2-251201
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY
      extra_headers:
        Connection: "close" 
      extra_body:
        thinking:
          type: "disabled" 
 
        
  - model_name: doubao-seed-1-8
    litellm_params:
      <<: *token_pricing
      model: volcengine/doubao-seed-1-8-251228
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY
      drop_params: true
      extra_headers:
        Connection: "close" 

  - model_name: doubao-seed-1-8-nothink
    litellm_params:
      <<: *token_pricing
      model: volcengine/doubao-seed-1-8-251228
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY
      extra_headers:
        Connection: "close"
      drop_params: true 
      extra_body:
        reasoning_effort: "minimal"        


#  - model_name: doubao-seed-2-0-pro
#    litellm_params:
#      <<: *token_pricing
#      model: volcengine/doubao-seed-2-0-pro-260215
#      api_base: os.environ/HUOSHAN_BASE_URL
#      api_key: os.environ/HUOSHAN_API_KEY
#      timeout: 1800 
#      drop_params: true 
#      extra_headers:
#        Connection: "close"

        
#  - model_name: doubao-seed-2-0-lite
#    litellm_params:
#      <<: *token_pricing
#      model: volcengine/doubao-seed-2-0-lite-260215
#      api_base: os.environ/HUOSHAN_BASE_URL
#      api_key: os.environ/HUOSHAN_API_KEY
#      drop_params: true
#      extra_headers:
#        Connection: "close"

  - model_name: doubao-seed-2-0-code
    litellm_params:
      <<: *token_pricing
      model: volcengine/doubao-seed-2-0-code-preview-260215
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY
      drop_params: true
      extra_headers:
        Connection: "close"

#禁用思考，用于标题等
  - model_name: doubao-seed-2-0-code-nothink
    litellm_params:
      <<: *token_pricing
      model: volcengine/doubao-seed-2-0-code-preview-260215
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY
      drop_params: true
      extra_headers:
        Connection: "close"
      extra_body:
#        thinking:
#          type: "disable"
        reasoning_effort: "minimal"

  # doubao-seed-2-0-code 强制中等思考，用作回退
  - model_name: doubao-seed-2-0-code-medium
    litellm_params:
      <<: *token_pricing
      model: volcengine/doubao-seed-2-0-code-preview-260215
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY
      timeout: 1800
      drop_params: true  
      extra_headers:
        Connection: "close"
      extra_body:
        reasoning_effort: "medium"

  - model_name: glm-5.2
    litellm_params:
      <<: *token_pricing
      model: volcengine/glm-5-2-260617
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY 
      extra_headers:
        Connection: "close"

#  - model_name: glm-4.7-nothink
#    litellm_params:
#      <<: *token_pricing
#      model: volcengine/glm-4-7-251222
#      api_base: os.environ/HUOSHAN_BASE_URL
#      api_key: os.environ/HUOSHAN_API_KEY 
#      extra_headers:
#        Connection: "close"
#      extra_body:
#        thinking:
#          type: "disabled" 

  #=======================fanyi

  - model_name: fanyi
    litellm_params:
      <<: *token_pricing
      model: volcengine/doubao-seed-1-8-251228
      api_base: os.environ/HUOSHAN_BASE_URL
      api_key: os.environ/HUOSHAN_API_KEY 
      timeout: 120 
      stream: false 
      drop_params: true
      extra_headers:
        Connection: "close"               
      extra_body:
        reasoning_effort: "minimal"    

#  - model_name: fanyi
#    litellm_params:
#      <<: *token_pricing
#      model: volcengine/doubao-seed-2-0-lite-260215
#      api_base: os.environ/HUOSHAN_BASE_URL
#      api_key: os.environ/HUOSHAN_API_KEY
#      timeout: 120 
#      stream: false 
#      drop_params: true
#      extra_headers:
#        Connection: "close"               
#      extra_body:
#        reasoning_effort: "minimal"

          





litellm_settings:
  #drop_params: true  #启用drop_params，这样LiteLLM会忽略不支持的参数，但参数仍然会传递给后端API
  num_retries: 3 # retry call 3 times on each model_name (e.g. zephyr-beta)
#  fallbacks: [
#    {"gemini-2.5-flash": ["gemini-2.5-pro"]}
#  ]
  default_fallbacks: ["doubao-seed-2-0-code-medium"]
  request_timeout: 120 # raise Timeout error if call takes longer than 10s. Sets litellm.request_timeout 
  cache: False          # 开启缓存
#  cache_params:
#    type: "redis"      # 指定使用 Redis
#    supported_call_types: ["completion", "embedding", "acompletion"] # 支持的类型  
  allowed_fails: 3 # cooldown model if it fails > 1 call in a minute.
  # 当前生效入口：volc_limit_sync.py
  # 监控模型发现、监控别名推导、资源包同步、HARD_DAILY_LIMITS 都在这个脚本里。
  # daily_limit.py 当前未启用，仅保留作历史参考。
  callbacks: ["volc_limit_sync.proxy_handler_instance"]

router_settings: # router_settings are optional
  routing_strategy: simple-shuffle 
  #model_group_alias: {"gpt-4": "gpt-4o"} # all requests with `gpt-4` will be routed to models with `gpt-4o`
  num_retries: 3
  timeout: 300                                  # 30 seconds
  #cooldown_time: 60
  
general_settings:
  store_model_in_db: false
  store_prompts_in_spend_logs: false  # <--- 这是最关键的一行