Original post · Original
The article text is unavailable in this language; an existing version is shown.
Not every incoming request has to trigger an additional LLM call to the frontier.
e.g. for a support request, what’s needed might be an answer, an action, or escalation.
The work should drive the routing, not a fixed rule. https://t.co/QsekEUkiqy
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,
View this post on X ↗
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
View this post on X ↗