Limitry Documentation

Usage metering for AI and LLM applications

Track AI consumption, enforce quotas, and integrate with billing platforms.

Choose Your Path

Why Limitry?

📊

Real-time Tracking

Track every API call, token, and resource in real-time.
🚦

Quota Enforcement

Set limits and enforce them before overage occurs.
💰

Billing Integration

Connect to Stripe, Orb, or any billing platform.

Sub-millisecond Latency

Check quotas without impacting your API response times.

Quick Start

New to Limitry? Get started in 3 steps:

  1. Learn the basics - Read the Quickstart to send usage data in 5 minutes.

  2. Understand the concepts - Learn about Core Concepts to understand events, quotas, and rate limits.

  3. Choose your SDK - Dive into the Python SDK or TypeScript SDK for hands-on guides.

Use Cases

Use CaseDescription
Token MeteringTrack LLM token consumption per customer
API Rate LimitingEnforce request limits per plan tier
Usage-Based BillingSend accurate usage data to your billing system
Cost AllocationAttribute AI costs to specific customers or projects

On this page