OpenRouter 推出 Jev Router:会话内动态调整模型推理强度
OpenRouter 出了个 Jev Router,同一个会话里自动调推理强度,切换前还会算上缓存丢失的成本,省钱思路挺实在。
OpenRouter 发布 Jev Router,可在同一会话内动态提高或降低模型推理强度,不必切换模型。它只在切换的预期收益大于成本时才切换模型,成本计算包含会丢失的缓存对话。这样整个会话能保持一个可用的模型。
Jev Router keeps a model that works for the rest of the session. It can raise or lower effort without switching models. It switches only when the expected gain is larger than the cost, including the cached chat it would lose. 💬 1 🔄 1 ❤️ 16 👀 3085 📊 3 ⚡