---
type: "post"
id: "vllm-semantic-router-releases-d3-ultra-a-26b-37f577"
slug: "vllm-semantic-router-releases-d3-ultra-a-26b-37f577"
title: "vLLM Semantic Router releases d3-ultra, a 26B open-weight multimodal decision model under Apache-2.0"
description: "vLLM Semantic Router has published d3-ultra on Hugging Face as the largest model in its Decision 3.0 family."
retrieval_nugget: "vLLM Semantic Router has published d3-ultra on Hugging Face as the largest model in its Decision 3.0 family."
published_at: "2026-10-27"
updated_at: "2026-10-27"
record_date: "2026-10-27"
date_kind: "published_at"
topics: ["generative-ui","agent-interfaces"]
entities: ["vLLM Semantic Router","d3-ultra","Hugging Face","AMD Instinct MI325X"]
related_patterns: ["model-answers-become-task-interfaces"]
novelty_label: "new_fact"
what_changed: "vLLM Semantic Router has released its own d3-ultra model: a 26B open-weight multimodal decision model under Apache-2.0, distinct from Liquid AI’s d1-ultra."
prior_refs: ["memory:97ea5922-c115-8ccd-add2-a1c2b600b4da","memory:ef75d338-446a-847c-ad86-b6b8ea802fac"]
source_url: "https://huggingface.co/vllm-sr/d3-ultra"
source_urls: ["https://huggingface.co/vllm-sr/d3-ultra"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:vllm-semantic-router-releases-d3-ultra-a-26b-37f577"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/vllm-semantic-router-releases-d3-ultra-a-26b-37f577/","markdown":"https://newruntime.com/posts/vllm-semantic-router-releases-d3-ultra-a-26b-37f577.md","json":"https://newruntime.com/posts/vllm-semantic-router-releases-d3-ultra-a-26b-37f577.json"}
---

# vLLM Semantic Router releases d3-ultra, a 26B open-weight multimodal decision model under Apache-2.0

## Retrieval answer

vLLM Semantic Router has published d3-ultra on Hugging Face as the largest model in its Decision 3.0 family.

vLLM Semantic Router has published d3-ultra on Hugging Face as the largest model in its Decision 3.0 family. The model card lists an Apache-2.0 licence and describes a 26.09B-parameter dense model, including a 0.46B vision encoder.

d3-ultra accepts text or JSON with images and video. Rather than generating free-form text, it returns probabilities for constrained tasks including multiple-choice selection, yes/no answers, scores, bounding boxes and video tracks. The card says one input can be read once and used to answer many questions, with up to 131,072 context tokens per question.

The authors report median latency from 304 ms for one question to 2.16 seconds for 255 questions about one photo on a single AMD Instinct MI325X. A free API at decision.vllm-sr.ai and a Hugging Face Space are listed. The reported 87.2 SR-Text result and other benchmarks are author-reported; the source does not establish independent evaluations, deployment cost, or production performance in routing, guardrail, or moderation systems.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Generative Ui](https://newruntime.com/topics/generative-ui.md): Explore the generative-ui topic hub.
- topic hub: [Agent Interfaces](https://newruntime.com/topics/agent-interfaces.md): Explore the agent-interfaces topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)