##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。 #=======================newapi # ⚠️ 单向依赖约定：litellm → newapi（OpenAI 兼容网关，必须用 openai/ 前缀）。 # ⚠️ 严禁在 newapi 后台添加任何回指本 litellm (192.168.1.238:23003) 的渠道， # 否则请求会在 litellm ↔ newapi 之间无限循环（循环风暴）。 - model_name: deepseek-v4-flash litellm_params: <<: *token_pricing model: openai/deepseek-v4-flash api_base: os.environ/NEWAPI_BASE_URL api_key: os.environ/NEWAPI_API_KEY - model_name: deepseek-v4-pro litellm_params: <<: *token_pricing model: openai/deepseek-v4-pro api_base: os.environ/NEWAPI_BASE_URL api_key: os.environ/NEWAPI_API_KEY #=======================火山平台，限时免费 - model_name: huoshan/deepseek-v4-flash litellm_params: <<: *token_pricing model: volcengine/deepseek-v4-flash-ga-260731 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true - model_name: huoshan/deepseek-v4-pro litellm_params: <<: *token_pricing model: volcengine/deepseek-v4-pro-ga-260813 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true - model_name: doubao-seed-2-1-turbo litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" model_info: max_input_tokens: 256000 # 允许的最大输入长度（单位：token） max_context_length: 256000 # 上下文窗口上限 - model_name: doubao-seed-2-1-pro litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" model_info: max_input_tokens: 256000 # 允许的最大输入长度（单位：token） max_context_length: 256000 # 上下文窗口上限 - 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 # 方舟 glm-5-2-260617 支持 reasoning_effort（none/minimal/high/max，默认 high； # 官方参数页 + 实测 curl 均确认），但 LiteLLM 的 VolcEngineChatConfig # get_supported_openai_params() 白名单里没有它 —— 它是 openai-like 的固定 # 参数表，不含 reasoning_effort —— 客户端一传就抛 UnsupportedParamsError。 # allowed_openai_params 是官方逃生口：get_optional_params 用它在校验前 # extend supported_params，随后 _apply_openai_param_overrides 把该参数从 # non_default_params 原样写回 optional_params，最终透传到请求体。 # 不用 drop_params：那是把该模型所有不支持参数静默丢弃，会掩盖其它真错。 # 注意 thinking.type 无需此项，VolcEngineChatConfig 已原生白名单。 allowed_openai_params: - reasoning_effort extra_headers: Connection: "close" model_info: max_input_tokens: 1024000 # 允许的最大输入长度（单位：token） max_context_length: 1024000 # 上下文窗口上限 #=======================豆包汇总nothink # 【思考档位别名组】doubao-seed-nothink / -minimal / -low / -medium / -high / fanyi # 语义：别名后缀即【默认】档位，非硬锁。 # - 客户端不传 reasoning_effort：按 extra_body 钉的档位发给方舟。 # - 客户端显式传 reasoning_effort：以客户端为准（覆盖默认档位）。 # 为什么钉不成硬锁（实测，本地 echo 抓上游 body）： # 请求带 reasoning_effort 时，Router._deployment_params_with_request_reasoning_override # 会【无条件】剥掉部署侧 extra_body.reasoning_effort / thinking； # 此时若没有 allowed_openai_params 放行，drop_params 又把客户端这个参数丢掉， # 两者同归于尽 ⇒ 上游 body 两者都没有 ⇒ 方舟回落默认 high（静默失效）。 # 故必须加 allowed_openai_params：让客户端值能通过校验，使结果至少是 # 「客户端说了算」而不是「悄悄变回 high」。 # LiteLLM 当前无纯配置手段做到「不论客户端传什么一律覆盖」；要硬锁只能加 # pre-call hook（本仓库当前不采用）。 # 注：方舟 doubao 上 minimal 等价于关闭思考（实测 reasoning_tokens=0）， # 故 nothink/minimal/fanyi 三个别名默认档位统一用 minimal。 - model_name: doubao-seed-nothink litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "minimal" - model_name: doubao-seed-nothink litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "minimal" #=======================豆包汇总思考等级minimal - model_name: doubao-seed-minimal litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "minimal" - model_name: doubao-seed-minimal litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "minimal" #=======================豆包汇总思考等级low - model_name: doubao-seed-low litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "low" - model_name: doubao-seed-low litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "low" #=======================豆包汇总思考等级medium - model_name: doubao-seed-medium litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "medium" - model_name: doubao-seed-medium litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "medium" #=======================豆包汇总思考等级high - model_name: doubao-seed-high litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "high" - model_name: doubao-seed-high litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "high" #=======================fanyi - model_name: fanyi litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-pro-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] drop_params: true extra_headers: Connection: "close" extra_body: reasoning_effort: "minimal" - model_name: fanyi litellm_params: <<: *token_pricing model: volcengine/doubao-seed-2-1-turbo-260628 api_base: os.environ/HUOSHAN_BASE_URL api_key: os.environ/HUOSHAN_API_KEY allowed_openai_params: ["reasoning_effort"] 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: [ #{"doubao-seed-high": ["deepseek-v4-pro"]} ] #default_fallbacks: ["deepseek-v4-flash"] 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。 # 旧脚本 archive/daily_limit.py.deprecated 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