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.
This is the 2nd launch from Inferock. View more
Inferock
Launching today
Get free signup credits to use all available models on Inferock.
Bring your own keys: run your OpenAI, Claude or Gemini accounts, see where calls fail and what they cost, and get credits back on eligible failed calls.
Serverless: pay-per-token LLM inference. Get signup credits to start using.
Free Options
Launch Team / Built With
Hi Product Hunt community, I’m Bharath, founder of Inferock.
Every team running LLMs in production pays for calls that came back empty, truncated, timed out, or returned broken JSON. You usually find out from a user, and you can’t prove it to anyone.
Inferock sits between your app and the provider and measures every call against a published baseline for quality, speed and cost. Each call gets a receipt that Inferock produces itself, so it doesn’t depend on the provider’s word.
Two ways to use it:
- Inferock Watch: bring your own OpenAI, Anthropic or Gemini keys. Free. You get the receipts and a monthly loss report. Enroll in the credit program and objectively broken calls accrue credits you can spend on Serve.
- Inferock Serve: serverless, pay-per-token inference through us. This is where your credits get spent.
How credits work: credits are non-cash, expire after 12 months, and are capped at $1,000 in the wallet and $1,000 applied per month. They cover verified, billed, unrecovered objective failures: downtime and timeouts, empty or truncated output, invalid structured output, billing and cache anomalies.
Tell us what the receipt should show that it doesn’t yet.
One thing we’ve learned while building this is that a failed LLM call is not always obvious.
Sometimes the request technically succeeds, but the output is incomplete, too slow, or unusable for the app.
That’s why we’re trying to make the receipt useful beyond just showing pass or fail. Curious what details you’d want to see on it when something goes wrong.
Thanks for hunting @fmerian!
It's not clear what should happen after that, should we contact Anthropic or openai for a refund for this calls?
Great question @bengeekly For Inferock Watch, we issue non-cash, expiring service credits for verified, billed, unrecovered failures.
Refusals, unbilled calls, and fully recovered costs earn no credit.
The wallet cap is $1,000 and the applied cap is $1,000 per calendar month; the service charge stays cash.
I love that it sits as a local proxy rather than requiring us to pipe sensitive request data tthrough a third party cloud dashboard.
This addresses a frustrating part of working with LLM APIs. I think having evidence of failures instead of relying on provider logs could make troubleshooting much easier for me
@gabrielemorello Thank you, that frustration is a big part of why Inferock exists.
Each call is measured by Inferock for quality, latency and cost, so you have your own record to troubleshoot from.
We'd love it if you have any more feedback!
I appreciate that Inferock Watch can work with my existing API keys. Being able to monitor calls without changing my entire setup makes the product more interesting to me
@gordonporter Thank you! That was a deliberate choice: Inferock Watch is free on your own provider keys, and your keys and provider billing stay with you.
The setup guide currently covers OpenAI, Anthropic and Gemini at inferock.ai/watch. If anything in setup feels heavier than it should, tell us. We want to hear it.
i think the strongest part is making inference failures measurable. My concern would be how the published quality baseline handles different use cases and models.
@almuddin_ansari Thank you, that is exactly the right thing to push on.
We work across multiple providers and not all of them return enough data to match our 'inferock standard'
So we do mark providers that allow us to provide 'full accounting' and 'basic accounting', the standard is continously evolving and we're always working towards making as many providers match the full baseline standard.
Let us know if you have any more questions!