Inferock

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.

Tracking quality, latency, and cost together sounds practical. I usually end up checking different logs and dashboards, so having one receipt for each call could help me understand issues faster.

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

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

I like the idea of getting a clear record of failed inference calls. When I’m debugging an AI workflow, knowing exactly what went wrong and what it cost would be genuinely useful.

​I just sent this over to our backend engineer. catching failed retries right when they happen is going to save us a lot on unexpected API costs.

It's not clear what should happen after that, should we contact Anthropic or openai for a refund for this calls?

Love the focus on transparency and accountability. Wishing the team great success! 👏

If the model returns invalid JSON, does it show exactly where the output broke?

Congrats @bharath_koneti 🙌

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.