返回探索

Jev为Claude Code提供智能模型路由

开发者在Claude Code前部署Jev路由器,每次调用仅花费约0.00002美元,即可将提示词智能分配给Haiku、Sonnet或Opus中最小且能胜任的模型,从而降低成本并优化延迟。

Every prompt I sent to Claude Code ran on Opus. Renames included. So I put a router in front of it: Jev sizes each prompt and hands it to the smallest model that can do the job (haiku / sonnet / opus). ~$0.00002 per decision. The real cost is latency.

· 0 次赞在 X 打开