计费
为内部团队和外部客户的用量计费
🚨 要求
- 设置 Lago，用于基于用量的计费。我们建议按照他们的 Stripe 教程进行操作
步骤：
- 将代理连接到 Lago
- 设置要计费的对象 ID（客户、内部用户、团队）
- 开始计费！
快速开始
为内部团队的用量计费
1. 将代理连接到 Lago
在您的代理 config.yaml 中将 'lago' 设置为回调
model_list:
- model_name: fake-openai-endpoint
litellm_params:
model: openai/fake
api_key: fake-key
api_base: https://exampleopenaiendpoint-production.up.railway.app/
litellm_settings:
callbacks: ["lago"] # 👈 关键更改
general_settings:
master_key: sk-1234
将您的 Lago 密钥添加到环境中
export LAGO_API_BASE="http://localhost:3000" # 自托管 - https://docs.getlago.com/guide/self-hosted/docker#run-the-app
export LAGO_API_KEY="3e29d607-de54-49aa-a019-ecf585729070" # 获取密钥 - https://docs.getlago.com/guide/self-hosted/docker#find-your-api-key
export LAGO_API_EVENT_CODE="openai_tokens" # lago 计费代码的名称
export LAGO_API_CHARGE_BY="team_id" # 👈 按代理密钥附加的 'team_id' 计费
启动代理
litellm --config /path/to/config.yaml
2. 为内部团队创建密钥
curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer sk-1234' \
--header 'Content-Type: application/json' \
--data-raw '{"team_id": "my-unique-id"}' # 👈 内部团队的 ID
响应对象：
{
"key": "sk-tXL0wt5-lOOVK9sfY2UacA",
}
3. 开始计费！
- Curl
- OpenAI Python SDK
- Langchain
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer sk-tXL0wt5-lOOVK9sfY2UacA' \ # 👈 团队的密钥
--data ' {
"model": "fake-openai-endpoint",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
}
'
import openai
client = openai.OpenAI(
api_key="sk-tXL0wt5-lOOVK9sfY2UacA", # 👈 团队的密钥
base_url="http://0.0.0.0:4000"
)
# 发送请求到 litellm 代理设置的模型，`litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
])
print(response)
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
SystemMessagePromptTemplate,
)
from langchain.schema import HumanMessage, SystemMessage
import os
os.environ["OPENAI_API_KEY"] = "sk-tXL0wt5-lOOVK9sfY2UacA" # 👈 团队的密钥
chat = ChatOpenAI(
openai_api_base="http://0.0.0.0:4000",
model = "gpt-3.5-turbo",
temperature=0.1,
)
messages = [
SystemMessage(
content="You are a helpful assistant that im using to make a test request to."
),
HumanMessage(
content="test from litellm. tell me why it's amazing in 1 sentence"
),
]
response = chat(messages)
print(response)
在 Lago 上查看结果
高级 - Lago 日志对象
这是 LiteLLM 将记录到 Lago 的内容
{
"event": {
"transaction_id": "<generated_unique_id>",
"external_customer_id": <selected_id>, # 可以是 'end_user_id', 'user_id', 或 'team_id'。默认 'end_user_id'。
"code": os.getenv("LAGO_API_EVENT_CODE"),
"properties": {
"input_tokens": <number>,
"output_tokens": <number>,
"model": <string>,
"response_cost": <number>, # 👈 LiteLLM 计算的响应成本 - https://github.com/BerriAI/litellm/blob/d43f75150a65f91f60dc2c0c9462ce3ffc713c1f/litellm/utils.py#L1473
}
}
}
高级 - 为客户、内部用户计费
对于：
- 客户（通过 /chat/completion 调用中的 'user' 参数传递的 ID）= 'end_user_id'
- 内部用户（设置密钥时设置的 ID）= 'user_id'
- 团队（设置密钥时设置的 ID）= 'team_id'
- 客户计费
- Internal User Billing
将 'LAGO_API_CHARGE_BY' 设置为 'end_user_id'
export LAGO_API_CHARGE_BY="end_user_id"测试它！
- Curl
- OpenAI Python SDK
- Langchain
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
"user": "my_customer_id" # 👈 whatever your customer id is
}
'import openai
client = openai.OpenAI(
api_key="anything",
base_url="http://0.0.0.0:4000"
)
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
], user="my_customer_id") # 👈 whatever your customer id is
print(response)from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
SystemMessagePromptTemplate,
)
from langchain.schema import HumanMessage, SystemMessage
import os
os.environ["OPENAI_API_KEY"] = "anything"
chat = ChatOpenAI(
openai_api_base="http://0.0.0.0:4000",
model = "gpt-3.5-turbo",
temperature=0.1,
extra_body={
"user": "my_customer_id" # 👈 whatever your customer id is
}
)
messages = [
SystemMessage(
content="You are a helpful assistant that im using to make a test request to."
),
HumanMessage(
content="test from litellm. tell me why it's amazing in 1 sentence"
),
]
response = chat(messages)
print(response)
- Set 'LAGO_API_CHARGE_BY' to 'user_id'
export LAGO_API_CHARGE_BY="user_id"
- Create a key for that user
curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{"user_id": "my-unique-id"}' # 👈 Internal User's id
Response Object:
{
"key": "sk-tXL0wt5-lOOVK9sfY2UacA",
}
- Make API Calls with that Key
import openai
client = openai.OpenAI(
api_key="sk-tXL0wt5-lOOVK9sfY2UacA", # 👈 Generated key
base_url="http://0.0.0.0:4000"
)
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
])
print(response)
