跳到正文
RadarAI· X:Rohan Paul (@rohanpaul_ai)·· 21 小时前AI 评分38

NaceAI 发布 Drex Router:57-87ms 为每次 LLM 调用选模型

AI 导读

NaceAI 发布小型路由模型 Drex Router,读取提示词和候选模型列表后约 57 到 87 ms 返回选择,基于 Gemma 的 12B 模型构建。在 1,400 道常识考题测试中准确率 87.6%,价格为每 1,000 题 $0.10,对比 Jev Router 为 86.4%、$1.09。它还会为每个候选模型返回概率和简短理由,而不只返回模型名。

正文 · 原文

Rohan Paul· @rohanpaul_ai · X·2026-11-21 05:48· 42 分钟前AI 评分54

AI 导读

@NaceAI 发布 Drex Router,一个小型路由模型,读取提示词和模型列表后约 57 到 87 ms 返回选择,基于 Gemma 的 12B 模型构建。在 1,400 道常识考题测试中准确率 87.6%,价格为每 1,000 题 $0.10;对比的 Jev Router 为 86.4%、$1.09。它还会为每个候选模型返回概率和简短理由,而不只返回模型名。

正文 · 原文

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: 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

来源:RadarAI · aihot.news