Inferock pitches inference with accountability: end-to-end encrypted inference, verifiable by design, with each route qualified with evidence, per its site.
Users choose how to run - their own provider accounts, managed serverless inference, or dedicated capacity - and Inferock records receipt evidence for each request, covering the route taken and the response returned.
The open-source inferock-bench project is a local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls, logging token usage, failures, and billing-integrity receipts; the repo showed 109 GitHub stars at review time.
