Inferly
Track every LLM call, token, cost, and latency in one place
什么是 Inferly？
Inferly captures metadata about every LLM API call — model, tokens, cost, latency, success — aggregates it, and shows it on a clean dashboard with spend alerting. Never touches prompt content.
截图
?
还没有评论，来抢沙发吧！
X 上关于 Inferly 的真实讨论
去 X 发帖