Lago

Lago는 셀프호스팅·클라우드로 제공되는 미터링(metering) 및 사용량 기반 과금(billing) 솔루션이에요. LiteLLM 콜백으로 성공한 호출의 비용·사용량을 Lago에 로깅하는 방법을 알려드릴게요.

출처: 문서

본문

빠른 시작 (Quick Start)

단 한 줄의 코드로 모든 프로바이더의 응답을 Lago에 즉시 로깅할 수 있어요.

Lago API Key를 받아 주세요.

litellm.callbacks = ["lago"] # logs cost + usage of successful calls to lago

SDK:

# uv add lago 
import litellm
import os

os.environ["LAGO_API_BASE"] = "" # http://0.0.0.0:3000
os.environ["LAGO_API_KEY"] = ""
os.environ["LAGO_API_EVENT_CODE"] = "" # The billable metric's code - https://docs.getlago.com/guide/events/ingesting-usage#define-a-billable-metric

# LLM API Keys
os.environ['OPENAI_API_KEY']=""

# set lago as a callback, litellm will send the data to lago
litellm.success_callback = ["lago"] 

# openai call
response = litellm.completion(
  model="gpt-5.6-luna",
  messages=[
    {"role": "user", "content": "Hi 👋 - i'm openai"}
  ],
  user="your_customer_id" # 👈 SET YOUR CUSTOMER ID HERE
)

PROXY:

Config.yaml에 추가

model_list:
- litellm_params:
    api_base: https://openai-function-calling-workers.tasslexyz.workers.dev/
    api_key: my-fake-key
    model: openai/my-fake-model
  model_name: fake-openai-endpoint

litellm_settings:
  callbacks: ["lago"] # 👈 KEY CHANGE

프록시 시작

litellm --config /path/to/config.yaml

테스트해 보세요!

Curl:

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
      "model": "fake-openai-endpoint",
      "messages": [
        {
          "role": "user",
          "content": "what llm are you"
        }
      ],
      "user": "your-customer-id" # 👈 SET YOUR CUSTOMER ID
    }
'

OpenAI Python SDK:

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-5.6-luna", messages = [
    {
        "role": "user",
        "content": "this is a test request, write a short poem"
    }
], user="my_customer_id") # 👈 whatever your customer id is

print(response)

Langchain:

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-5.6-luna",
    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)

고급 — Lago 로깅 객체 (Advanced - Lagos Logging object)

LiteLLM이 Lago에 로깅하는 객체예요.

{
    "event": {
      "transaction_id": "<generated_unique_id>",
      "external_customer_id": <litellm_end_user_id>, # passed via `user` param in /chat/completion call - https://platform.openai.com/docs/api-reference/chat/create
      "code": os.getenv("LAGO_API_EVENT_CODE"), 
      "properties": {
          "input_tokens": <number>,
          "output_tokens": <number>,
          "model": <string>,
          "response_cost": <number>, # 👈 LITELLM CALCULATED RESPONSE COST - https://github.com/BerriAI/litellm/blob/d43f75150a65f91f60dc2c0c9462ce3ffc713c1f/litellm/utils.py#L1473
      }
    }
}

더 알아보기 (Learn more)

Lago — 셀프호스팅·클라우드 미터링 및 사용량 기반 과금 솔루션