Text analysisModeration and safety

vLLM Semantic Router: Decision и Vela

An open family of models for an AI gateway: they answer a request with probabilities without generating text. They detect topic and urgency, jailbreak attempts, harmful requests, personal data and whether a tool is needed. Small versions run on a CPU, Vela understands 17 languages including Russian.

Developer
vLLM Semantic Router project, international project
First release
Sep 2026
Latest release
Oct 2026
Sizes
0.3B – 27B
License
Commercial use allowedApache 2.0
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Security, Customer support, Software development, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • routing requests between models and teams
  • checking a request for a jailbreak attempt or harmful content before the main model
  • finding personal data with positions in a text
  • spotting claims in an AI answer with no source behind them

Where it is used

AI gateways and corporate assistantsinformation securitycustomer support

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Vela 2.0 (0.3B, 0.8B, 4B, 9B)
  2. Decision 2.0 (Kai 0.6B, Eos 0.8B, Sol 2B, Nox 4B, Lux 9B, Vega 27B)
  3. Decision 1.0 (Kai, Eos, Lux, Route 0.6B)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can vLLM Semantic Router: Decision и Vela be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does vLLM Semantic Router: Decision и Vela need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does vLLM Semantic Router: Decision и Vela support Russian?

Yes, Russian is listed on the model card.

Where can I download vLLM Semantic Router: Decision и Vela and what does it cost?

The vLLM Semantic Router: Decision и Vela weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Text analysisClefCloudflare · USACommercial use allowed

Decision models: they do not write text but read a situation (text, JSON, an image, video frames) and return in one pass the probability of each answer to typed questions: yes or no, pick one, rate on a scale. The agent gets ready numbers instead of parsing free text.

DetailsText analysisJEV и GEVAutoTrust AI · SingaporeCommercial use allowed

Open decision models: for yes/no, pick-one and rate-0-to-5 questions they answer with probabilities in one pass, and can also reason when needed. Not affiliated with the closed Jev from TypeSafe.

DetailsText analysisLiquid d1Liquid AI · USACommercial use with conditions

Small decision models: from text, an image or a voice clip they answer yes or no, pick an option or give a rating in one pass, without writing text. d1-3B sees images, d1-omni-600M also hears speech up to 30 seconds. Russian is listed.

Details

Source: huggingface.co/vllm-sr/Vela-2.0-0.3B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.