aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分40

NaceAI 推出 Drex Router,为每次模型调用选择模型和推理强度

AI 导读

Drex Router 读取提示词和候选模型列表,返回推荐模型、每个候选模型的概率及简短理由。发布帖称,路由结果约需 57 至 87 毫秒;在 Nace 的 1,400 道常识考试题测试中,其准确率为 87.6%,每 1,000 题成本为 0.10 美元。这些数字来自发布方测试。

原帖引用 · 原文

@rohanpaul_ai

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,

引用Nace AI@NaceAI
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://t.co/sosFYHDDet COMMENT DREX and get extra $5 in API credits https://t.co/YOKMA5jOBp
在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

产品
发现内容有误?提交纠错