NaceAI 推出 Drex Router,这是一个基于 Gemma 的 12B 小模型,读取提示词和候选模型列表后返回选择,决策耗时约 57 至 87 毫秒。在 Nace 的 1400 道通用知识考题测试中,它得分 87.6%,每 1000 题成本 $0.10,竞品 Jev Router 得分 86.4%、成本 $1.09。该路由还会为每个候选模型返回概率和简短理由,而不只是给出模型名。
A model decision in under 90 ms is fast enough to put a router in front of almost any LLM call.
@NaceAI just launched Drex Router, and it reads the prompt and your list of models, then returns its pick in about 57 to 87 ms, using a 12B model built on Gemma.
In Nace’s tests on 1,400 general-knowledge exam questions, it scored 87.6% for $0.10 per 1,000 questions, while rival Jev Router scored 86.4% for $1.09.
A router that only returns a model name can’t tell you a confident pick from a coin flip. Drex Router returns a probability for every candidate plus a short reason,
Introducing Drex Router. A small model that picks the right LLM/SLM and reasoning effort for every step your agent takes. Accuracy: Drex Router 87.6% vs. Jev Router’s 86.4% Try it: https://console.nace.ai COMMENT DREX and get extra $5 in API credits在 X 查看被引用的帖子
来源:Rohan Paul · x.com