AI Module Overview
The Antarctica AI Module is your one-stop shop for monitoring how your apps are using Large Language Models (LLMs). We provide a set of simple endpoints designed to catch, track, and aggregate your AI telemetry data.
What’s in it for you?
By piping your AI usage data to us, you can finally answer those tricky observability questions:
- Token Spend: See exactly how many tokens you’re burning on
inputandoutputacross different models and providers. - Performance: Track response performance and throughput across your AI calls.
- Cost Control: Get a clear breakdown of your spend whether you’re using OpenAI, Claude, Gemini, or all three.
The OTM’s hardware calibration database and model profiles are proprietary and are not surfaced through the API. The API receives usage telemetry and returns computed outputs. Internal calibration parameters are not accessible via any endpoint.
Why use our AI Module?
- Dead Simple Ingestion: Our OTM API is built to handle millions of events without breaking a sweat, running entirely in the background.
- Clean Data: We use strict schemas so your analytics dashboards stay reliable and error-free.
- Idempotency Built-In: Don’t worry about duplicate data. If a network blip causes a retry, we handle it gracefully.
Ready to get started? Head over to the Setup Guide to grab your API keys and start shipping data.