---
format: "aidr-story-markdown/v1"
id: "887b618ab35cb0bb1596da839823cfbfe9147be2a9896e4d4918ea8b70a7d484"
canonical_url: "https://aidr.today/887b618a?lang=en"
title: "vLLM Semantic Router Releases d3-ultra: A 27B Open Multimodal Decision Model"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-27T05:50:57.000Z"
category: "Models"
topics: ["llm"]
source_urls: ["https://www.marktechpost.com/2026/10/26/vllm-semantic-router-d3-ultra-27b-multimodal-decision-model/"]
summary: "vLLM Semantic Router released d3-ultra, a 27B open-weight multimodal decision model that processes text, images, and video to return probabilities for answers, scoring 87.2 on the team's SR-Text test."
---

# vLLM Semantic Router Releases d3\-ultra: A 27B Open Multimodal Decision Model

> [Open the canonical story](<https://aidr.today/887b618a?lang=en>)

**Published:** 2026-10-27T05:50:57.000Z
**Category:** Models
**Topics:** llm

## Summary

vLLM Semantic Router released d3\-ultra, a 27B open\-weight multimodal decision model that processes text, images, and video to return probabilities for answers, scoring 87\.2 on the team's SR\-Text test\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/10/26/vllm-semantic-router-d3-ultra-27b-multimodal-decision-model/>)