tokentifyai-usagemeter 0.1.2

Out-of-band AI API usage metering SDK

Tokentify UsageMeter (Python)

Out-of-band AI API usage metering for Python. After setup, use httpx for provider calls; the SDK captures usage automatically.

Install

pip install tokentifyai-usagemeter

Optional virtual environment:

python3 -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install tokentifyai-usagemeter

Setup

1. Environment (API key is global)

Copy .env.example to .env. The API key lives only in .env (or your deployment environment)—never in init() code.

cp .env.example .env

# .env — required
USAGEMETER_API_KEY=your_ingest_api_key
USAGEMETER_BUCKET=your_bucket_name

2. Initialize

import os
import tokentifyai_usagemeter as um

# USAGEMETER_API_KEY from .env; USAGEMETER_BUCKET from argument
um.load_env()
um.setup(os.environ["USAGEMETER_BUCKET"])

# USAGEMETER_API_KEY and USAGEMETER_BUCKET both from .env
um.setup()

# Production (skip health checks after first successful setup)
um.load_env()
um.init(
    os.environ["USAGEMETER_BUCKET"],
    verify_connection=False,
    verify_api_key=False,
)

Function	When to use
setup() / setup(USAGEMETER_BUCKET value)	First run; verifies collector + USAGEMETER_API_KEY from .env
init() / init(USAGEMETER_BUCKET value)	Same; control verify_connection / verify_api_key

Init parameters (API key is not accepted):

Parameter	Source
bucket	Argument (value of USAGEMETER_BUCKET) or USAGEMETER_BUCKET in .env
app_name	Argument or USAGEMETER_APP_NAME in .env
environment	Argument or USAGEMETER_ENVIRONMENT in .env (default production)
load_env_file	Default True — loads .env before reading env vars
verify_connection	Default False (True in setup)
verify_api_key	Default True

# Not supported — will raise TypeError:
# um.init(os.environ["USAGEMETER_BUCKET"], api_key="secret")

Call init() / setup() before creating httpx clients.

3. Launch (v0.1.2)

.env (USAGEMETER_API_KEY + USAGEMETER_BUCKET):

USAGEMETER_API_KEY=your_ingest_api_key
USAGEMETER_BUCKET=your_bucket_name

app.py:

import httpx
import tokentifyai_usagemeter as um

um.setup()  # loads .env; reads USAGEMETER_API_KEY and USAGEMETER_BUCKET

client = httpx.Client()
response = client.post(
    "https://api.openai.com/v1/chat/completions",
    json={"model": "gpt-4o", "messages": [{"role": "user", "content": "hi"}]},
    headers={"Authorization": "Bearer YOUR_OPENAI_KEY"},
)
print(response.status_code)

um.flush()

python app.py

4. Develop from this repo

cd tokentify-sdk-python
python -m venv .venv && source .venv/bin/activate
pip install -e .
cp .env.example .env   # set USAGEMETER_API_KEY and USAGEMETER_BUCKET
python -c "import tokentifyai_usagemeter as um; um.setup(); print(um.is_initialized())"