ToolsCostAPI

Inferock launches per-call receipts for LLM API calls, free on your own keys

Inferock ·

Inferock marketing card on a pale gray background with the Inferock wordmark and pink logo at top left, the line Accountable inference. Across every tier., the headline Run inference with accountability. with accountability in blue, and the text Choose how you run: your provider accounts, managed serverless inference, or dedicated capacity.
Image: Inferock

Inferock (inferock.ai) routes LLM API calls and records an independent receipt for each one, covering usage, timing, failures and cost evidence. Inferock Watch is free on your own provider keys (your providers still bill you). It's visibility only, with no automatic credit. On the prepaid Inferock Serve plan, Inferock says eligible objective failures like timeouts, broken or invalid output and billing anomalies can earn capped, non-cash service credits under agreed terms. Credits aren't cash refunds, apply only to future Serve usage and can expire. Its local measurement proxy, inferock-bench, is source-available. Launched on Product Hunt Oct 14. (Inferock)

How you’d use it: If you want a record of what each model call cost and where calls fail, try the free Watch tier on your own provider keys; it only watches and gives no credits. Read the Serve terms before counting on credits: they're capped, non-cash, only usable on future Serve usage and they expire.

Sources

← All AI news

Get the daily AI news

The day's important AI news by email: short, plain summaries, each linked to its source. Unsubscribe any time.

Prefer email? Write to [email protected] ([email protected]).