Does Qwen3 VL 30B A3B Thinking support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen3 VL 30B A3B Thinking is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Qwen3 VL 30B A3B Thinking hosted?

Qwen3 VL 30B A3B Thinking runs on US hosting routes through the Opper gateway.

Is Qwen3 VL 30B A3B Thinking trained on prompts and outputs?

No. Every hosting route for Qwen3 VL 30B A3B Thinking is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3 VL 30B A3B Thinking?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3 VL 30B A3B Thinking. Contact hello@opper.ai to receive it.

Qwen3 VL 30B A3B Thinking

by Alibaba

Qwen3 VL 30B A3B Thinking pairs an efficient MoE architecture (30B parameters, about 3B active) with explicit reasoning traces for complex visual problems. The thinking mode generates step-by-step reasoning before the final answer, producing interpretable solutions across multimodal tasks. It fits visual reasoning benchmarks, math problem-solving with images, and spatial reasoning where understanding the model's visual reasoning process is important. With a 131K context window, it handles long documents and video analysis, and it scores strongly on competition math such as AIME 2025. The model bridges efficiency and reasoning transparency, making it suitable for educational visual AI, visual mathematics tutoring, and research applications. The open-weight release enables fine-tuning on specialized visual reasoning domains and local deployment.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

33K

Input price

$0.20 /1M

Output price

$1.00 /1M

US residency available
Zero data retention via Enterprise
No training by default
GDPR DPA available

Available routes

Qwen3 VL 30B A3B Thinking 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
Novita	US	Enterprise	No	$0.20	$1.00

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

Data handling per route

Each route hosting Qwen3 VL 30B A3B Thinking has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Novita — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Qwen3 VL 30B A3B Thinking 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: "novita/qwen/qwen3-vl-30b-a3b-thinking",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);