Varun Rajput

Building Multi Tenant LLM Usage Tracker

About

Hey, I'm Varun. ML Platform Engineer with 11+ years in infrastructure, managed 100+ Kubernetes clusters and 100+ GPUs in production. Currently building TokenTrail because I got tired of surprise LLM bills and manually tracking costs per customer in spreadsheets.

Badges

Gone streaking

Forums

•

3d ago

Helicone tracks your costs. We bill your customers. $5 free to try

You're paying OpenAI/Anthropic per token. Your customers are using your app. Somewhere in between, there's a spreadsheet, manual invoices, and zero idea who's burning through your budget.

TokenTrail closes that gap:

tracks usage per customer
hard budget limits that actually stop requests
auto-generates invoices

•

9d ago

TokenTrail: auto-invoice your customers for LLM usage.The billing layer between Helicone and Stripe.

I have seen companies keep getting hit with surprise LLM bills, retry loops, users spamming AI features, and no way to know which customer caused a cost spike. So I started building TokenTrail to fix it for myself and figured others might have the same problem.

What it does:

Set hard budget limits that kill requests at $X (no more Monday morning surprises, though customisable from the user side)
Track cost per customer, not just total API spend
See what each step in a multi-agent workflow actually costs
Basic smart routing to cheaper models for simple queries
LiteLLM integration