Does Qwen3 30B A3B support zero data retention?

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

Where is Qwen3 30B A3B hosted?

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

Is Qwen3 30B A3B trained on prompts and outputs?

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

Qwen3 30B A3B

by Alibaba

Qwen3-30B-A3B is Alibaba's efficient MoE model released in April 2025, with 30.5 billion total parameters and only 3.3 billion activated per token through 128 experts (8 selected). This sparse design delivers low inference cost while keeping broad capability across reasoning, coding, and general tasks. The model supports switching between a step-by-step reasoning mode for complex problems and direct generation for straightforward queries within a single architecture. Native context covers around 40K tokens, extending to 131K via YaRN, and it handles mathematical reasoning, code generation, and instruction following across 100+ languages, drawing on roughly 36 trillion tokens of pretraining data. Both thinking and non-thinking modes let users match computational depth to task complexity. MoE sparse activation means the inference cost reflects only a fraction of the full 30.5 billion parameters. Open-weight under Apache 2.0.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

41K

Max output

41K

Input price

$0.09 /1M

Output price

$0.45 /1M

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

Available routes

Qwen3 30B A3B 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
DeepInfra	US	Enterprise	No	$0.09	$0.45

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

Data handling per route

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

DeepInfra — United States🇺🇸

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

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Limited debug logs
Third-party access: None disclosed
GDPR DPA: No DPA
Transfer mechanism: unknown

Benchmarks

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

Global rank#245 of 534 LLMs

TierEfficient

Output speed144 tok/s

First token0.97s

Intelligence Index15.8

Math Index56.3

Reasoning & knowledge

MMLU-Pro

81%

GPQA Diamond

71%

Humanity's Last Exam

10%

Long-context reasoning

59%

Coding

LiveCodeBench

71%

SciCode

33%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

28%

Math & instruction following

AIME 2025

56%

IFBench

51%

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

Get started

Call Qwen3 30B A3B 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: "deepinfra/Qwen/Qwen3-30B-A3B",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);