Local proxy that gives per-call billing receipts for OpenAI, Anthropic, and Gemini calls
inferock-bench is a local cost-tracking proxy for LLM API calls to OpenAI, Anthropic, Gemini, and pinned OpenRouter models. It gives an independent, per-call receipt of what was billed and what failed, so developers can audit an AI or LLM bill call by call.
It's built for measuring Claude or GPT token usage locally and checking whether you were billed for a failed API call, giving developers visibility into their LLM spend independent of the provider's own reporting.
inferock-bench is a local LLM cost-tracking proxy that gives per-call billing receipts for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls.
It's for developers who want to audit their AI/LLM bill and measure Claude or GPT token usage locally.
It can check whether you were billed for a failed API call, based on an independent per-call receipt.
It supports OpenAI, Anthropic, Gemini, and pinned OpenRouter calls.