返回全部资讯
Rohan Paul (@rohanpaul_ai)T2·开发与工程

Nace 推出 12B 模型路由器 Drex 延迟低于 90 ms

原标题:A model decision in under 90 ms is fast enough to put a router in front of almost any LLM call.
62AI 研判分

Nace AI 发布 Drex Router,基于 Gemma 构建的 12B 模型读取提示词与候选模型列表,在 57 至 87 毫秒内返回模型选择、每个候选的概率及简短理由。在 1400 道通用知识考题测试中准确率 87.6%,每千题成本 0.10 美元,对比 Jev Router 的 86.4% 与 1.09 美元。

报道正文

Rohan Paul (@rohanpaul_ai) · 2026-11-20 21

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 @NaceAI (Nace AI): 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

推文配图

推文配图