Does Qwen3 VL 8B Instruct support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen3 VL 8B Instruct is available on request via Opper Enterprise — contact hello@opper.click.

Where is Qwen3 VL 8B Instruct hosted?

Qwen3 VL 8B Instruct runs on US hosting routes through the Opper gateway.

Is Qwen3 VL 8B Instruct trained on prompts and outputs?

No. Every hosting route for Qwen3 VL 8B Instruct is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3 VL 8B Instruct?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3 VL 8B Instruct. Contact hello@opper.click to receive it.

Qwen3 VL 8B Instruct

by Alibaba

Qwen3 VL 8B Instruct is an open-weight, compact dense vision-language model offering multimodal understanding for image-to-text tasks, GUI automation, and visual reasoning. With about 9 billion parameters and a 131K context window, it balances capability with a low memory footprint for edge and resource-constrained deployments. The model works across visual domains, including spatial perception, OCR in 32 languages, visual coding assistance, and document analysis. It supports visual agent functions for interface navigation while staying efficient at inference. It is well suited to local deployment, edge AI systems, and applications that prioritize latency over maximum visual reasoning capability. The dense architecture and open-weight release enable fine-tuning for specialized visual domains and on-device vision systems.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

33K

Input price

$0.08 /1M

Output price

$0.50 /1M

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

Available routes

Qwen3 VL 8B Instruct 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	$0.08	$0.50

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

Data handling per route

Each route hosting Qwen3 VL 8B Instruct 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

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#371 of 534 LLMs

TierEfficient

Output speed145 tok/s

First token0.93s

Intelligence Index8.4

Math Index27.3

Reasoning & knowledge

MMLU-Pro

69%

GPQA Diamond

43%

Humanity's Last Exam

Long-context reasoning

15%

Coding

LiveCodeBench

33%

SciCode

17%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

29%

Math & instruction following

AIME 2025

27%

IFBench

32%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Qwen3 VL 8B Instruct 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.click/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "novita/qwen/qwen3-vl-8b-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);