Inferock
An independent receipt for every LLM API call
Start new thread

Inferock Bench - An independent receipt for every LLM API call

by
•
Inferock-bench is a local proxy that sits between your app and OpenAI, Anthropic, Gemini, or OpenRouter shaped calls. It captures per-call token usage, failures, and retries, then generates an independent receipt showing what you were billed and how much you're actually overpaying for.

Add a comment

Replies

Best

Retries are the part I’d put in giant font. ‘$0.04/call’ means nothing if a successful job secretly takes 6 calls. I want cost per accepted outcome.

Maker
Cost per accepted outcome is a really good way to put it. Today the receipt shows all six of those calls and what each one cost, so the secret multiplier at least stops being secret. But the roll-up per outcome is a good suggestion. We’ll try to incorporate in the following revisions!

Congrats on the launch of Inferock Bench.

Love the idea of having an independent receipt for every LLM API call. Transparent usage, billing, and overpayment tracking can be a huge win for teams working with multiple LLM providers.

Maker
Thank you so much! Multi-provider teams are exactly where things get messy fastest, a different bill from everyone and no shared way to check any of them. Hope it takes some of that pain off your plate.
First
Previous
123