Does Qwen 3 VL 30B support zero data retention?

Yes. Qwen 3 VL 30B is available with zero data retention by default on Evroc through the Opper gateway.

Where is Qwen 3 VL 30B hosted?

Qwen 3 VL 30B runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Qwen 3 VL 30B trained on prompts and outputs?

No. Every hosting route for Qwen 3 VL 30B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen 3 VL 30B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen 3 VL 30B. Contact hello@opper.ai to receive it.

Qwen 3 VL 30B

by Alibaba

Qwen 3 VL 30B is an open-weight mixture-of-experts vision-language model (30B base, about 3B active) aimed at production visual agent work, code generation from images, and document understanding. With a 131K context window, it processes long documents, multi-page PDFs, and video without truncation. It automates GUIs across PC and mobile interfaces, generates HTML and CSS from design mockups, runs multilingual OCR with 32-language support, and reasons about object detection and viewpoint. Its visual perception is paired with text understanding aligned to the pure language models in the series. It is a good fit for document processing pipelines, visual automation systems, and production multimodal RAG where visual agent functionality matters more than explicit reasoning. The open-weight release enables local deployment and fine-tuning for domain-specific visual understanding.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

Input price

$0.22 /1M

Output price

$0.86 /1M

EU residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Qwen 3 VL 30B runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Evroc	EU	Zero data retention	No	$0.22	$0.86

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Qwen 3 VL 30B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Evroc — Sweden🇸🇪

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Qwen 3 VL 30B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "evroc/qwen3-vl-30b-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);