Does Qwen3 8B support zero data retention?

Yes. Qwen3 8B is available with zero data retention on Greenference through the Opper gateway.

Where is Qwen3 8B hosted?

Qwen3 8B runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Qwen3 8B trained on prompts and outputs?

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

Is a GDPR DPA available for Qwen3 8B?

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

Qwen3 8B

by Alibaba

Qwen3 8B is the compact dense model of Alibaba's April 2025 Qwen3 release. It shares the family's hybrid design: a thinking mode that reasons step by step through math, code and logic, and a non-thinking mode for fast direct replies, with tool calling available in both. Trained on data spanning more than a hundred languages and dialects, it covers classification, extraction, chat and short agent loops where a larger model would be overkill. It is released under Apache 2.0 and suits high-volume workloads that want optional reasoning at small-model cost and latency.

Call Qwen3 8B on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

33K

Max output

—

Input price

$0.45 /1M$0.22 cache read

Output price

$0.45 /1M

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

Available routes

Qwen3 8B runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Greenference	EU		No	$0.45	$0.45	$0.22

Data handling per route

Each route hosting Qwen3 8B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Greenference — European Union🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
Subprocessor access: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Benchmarks

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

Global rank#485 of 662 LLMs

TierEfficient

Intelligence Index7.3

Coding Index9.0

Math Index19.0

Reasoning & knowledge

MMLU-Pro

74%

GPQA Diamond

59%

Humanity's Last Exam

Long-context reasoning

Coding

LiveCodeBench

41%

SciCode

28%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

28%

Math & instruction following

AIME 2025

19%

IFBench

33%

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

Get started

Call Qwen3 8B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen3 8B is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex 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: "greenference/qwen3-8b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);