kim/litellm-config
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
8a6416f28fe9b2ec7955ceb6b9c1707e6ab191cb
litellm-config/config.yaml
T
vibe-code d9c7b1406d refactor: 目录整理配套引用同步 
README/AGENTS 文件清单与命令更新为新结构（generate_keys -> scripts/、
daily_limit -> archive/、文档 -> docs/）；config.yaml 与 volc_consume.py
注释中废弃脚本/文档路径同步；README 过期限额示例更新为 2M 配置。
2026-08-12 06:58:16 +00:00

492 lines
15 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
##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
###
#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_info:
# max_input_tokens: 128000 # 允许的最大输入长度（单位：token）
# max_context_length: 128000 # 上下文窗口上限
# - 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: 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
drop_params: true
- 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"
model_info:
max_input_tokens: 224000 # 允许的最大输入长度（单位：token）
max_context_length: 256000 # 上下文窗口上限
#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"
model_info:
max_input_tokens: 224000 # 允许的最大输入长度（单位：token）
max_context_length: 256000 # 上下文窗口上限
# 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_info:
max_input_tokens: 224000 # 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-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
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
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
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
- model_name: doubao-seed-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:
reasoning_effort: "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
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
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-2-0-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:
reasoning_effort: "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
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
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-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"
extra_body:
reasoning_effort: "high"
- model_name: doubao-seed-low
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:
reasoning_effort: "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
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
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-2-0-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:
reasoning_effort: "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
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
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-2-0-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:
reasoning_effort: "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
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
drop_params: true
extra_headers:
Connection: "close"
extra_body:
reasoning_effort: "high"
#=======================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: [
{"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
Reference in New Issue View Git Blame Copy Permalink