d3-ultra
d3-ultra is a 27B multimodal decision model that accepts text or JSON, optionally with images and videos, and returns answers with probabilities rather than generating text. It supports choice, yes/no, scoring, box localization, and video tracking decisions, with up to 131,072 tokens per question.
What it does
Use it to classify or score inputs, answer multiple questions about images and videos, and locate or track objects in visual content.
- Availability
- Free API at decision.vllm-sr.ai; model on Hugging Face
- Pricing model
- Free API
- Deployment
- Free API and local use with Transformers
- Privacy
- Not established
- Licence
- Apache-2.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- Accepts text or JSON, optionally with images and videos. [1]
Give it an input (text or JSON, optionally with images and videos) and the questions you need answered: pick one of several options, say yes or no, rate on a scale, or point to where something is in an image or a video.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Supports choice, yes/no, score, box, and video-track decision types. [1]
| **Decision types** | Choice · Yes / No · Score · Box (images and video moments) · Track (whole videos) |
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Returns a probability for every answer without generating text. [1]
It reads the input once per request, answers every question on it, and returns a probability for every answer, without generating text.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Supports up to 131,072 tokens per question. [1]
| **Context** | 131,072 tokens per question |
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The free API serves d3-ultra at decision.vllm-sr.ai. [1]
**Try it free** at [decision.vllm-sr.ai](https://decision.vllm-sr.ai): the free API serves d3-ultra · Official Space: [vllm-sr/d3-ultra](https://huggingface.co/spaces/vllm-sr/d3-ultra)
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model can be loaded from vllm-sr/d3-ultra using Transformers. [1]
Sources
1
1
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-29 00:21 UTC | material change | access, deployment, availability, deployment | Current |
| 1 | 2026-10-27 00:11 UTC | publication | None | Current |
In briefs
1- Create expressive speech from a short voice sample Daily brief 2026-10-27
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.