Skip to main content

​
1. Get Your API Key

  1. Sign in to the Limitry Dashboard
  2. Navigate to your project settings
  3. Copy your Project API Key
Your API key looks like: limitry_sk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

​
2. Install the SDK

pip install limitry

​
3. Check and Record Usage

The core pattern is Check → Request → Record: 
import os
from limitry import Limitry
from openai import OpenAI

limitry = Limitry(api_key=os.environ.get("LIMITRY_API_KEY"))
openai = OpenAI()

customer_id = "cust_123"

# 1. Check if customer is within limits
check = limitry.limits.check(customer_id=customer_id)

if not check.allowed:
    print("Limit exceeded!")
else:
    # 2. Make your request
    response = openai.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    
    # 3. Record the usage event
    limitry.events.record(
        customer_id=customer_id,
        event_type="llm.completion",
        values={"tokens": response.usage.total_tokens},
        dimensions={"model": "gpt-4"}
    )

​
4. Create a Meter and Limit

Set up metering and limits for your customers: 
# Create a meter to sum tokens
meter = limitry.meters.create(
    name="Total Tokens",
    event_type="llm.completion",
    aggregation="sum",
    value_key="tokens"
)

# Create a limit using that meter
limit = limitry.limits.create(
    name="Daily token limit",
    meter_id=meter.id,
    limit_value=100000,
    period="day",
    customer_id="cust_123"
)

​
Next Steps

Events

Learn about the generic event structure

Meters

Define how usage is aggregated

Limits

Set up usage caps

Balances

Manage prepaid credits