Skip to main content
nozle.track(
    customer_id="customer_123",
    event="api_call",
    metadata={"model": "gpt-4", "tokens": 1500},
    subscription_id="sub_abc",      # optional
    transaction_id="tx_unique",     # optional, for idempotency
    timestamp="2024-01-15T10:30:00Z",  # optional
)

​
Parameters

  • customer_id (str): External customer ID
  • event (str): Event code matching a billable metric in your workspace
  • metadata (dict, optional): Properties for aggregation
  • subscription_id (str, optional): Target specific subscription
  • transaction_id (str, optional): Idempotency key (auto-generated if omitted)
  • timestamp (str, optional): ISO 8601 timestamp
This calls POST /api/v1/events on the Nozle API with the same payload format as the Node SDK.

​
Example — Track LLM usage in a FastAPI app

from fastapi import FastAPI
from nozle import Nozle
import openai

app = FastAPI()
nozle = Nozle(api_key="sk_...", base_url="https://api.nozle.app", events_url="https://api.nozle.app")

@app.post("/chat")
async def chat(customer_id: str, message: str):
    response = openai.chat.completions.create(
        model="gpt-4", messages=[{"role": "user", "content": message}]
    )
    nozle.track(
        customer_id=customer_id,
        event="llm_tokens",
        metadata={
            "model": response.model,
            "tokens": response.usage.total_tokens,
        },
    )
    return {"reply": response.choices[0].message.content}