Does Qwen3.5 2B support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen3.5 2B is available on request via Opper Enterprise — contact hello@opper.click.

Where is Qwen3.5 2B hosted?

Qwen3.5 2B runs on US hosting routes through the Opper gateway.

Is Qwen3.5 2B trained on prompts and outputs?

No. Every hosting route for Qwen3.5 2B is configured so customer prompts and outputs are not used to train models by default.

Qwen3.5 2B

by Alibaba

Qwen3.5 2B is a lightweight 2 billion parameter dense model designed for efficient deployment while keeping multimodal vision-language capability, built on a hybrid architecture that pairs Gated DeltaNet with attention layers. It supports a 262,144 token native context window and runs in non-thinking mode by default for faster responses. Reported results include MMLU-Pro 55.3 and MMMU 64.2, with the model handling text, image, and video inputs across more than 200 languages. Thinking mode can be enabled when a task calls for step-by-step reasoning. Its small footprint makes it well suited to prototyping, task-specific fine-tuning, and resource-constrained scenarios where a compact multimodal model is preferred.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.02 /1M

Output price

$0.10 /1M

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

Available routes

Qwen3.5 2B 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	$0.02	$0.10

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

Data handling per route

Each route hosting Qwen3.5 2B 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#320 of 534 LLMs

TierEfficient

Output speed28 tok/s

First token0.44s

Intelligence Index10.2

Coding Index19.7

Reasoning & knowledge

GPQA Diamond

46%

Humanity's Last Exam

Long-context reasoning

24%

Coding

SciCode

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

69%

Math & instruction following

IFBench

31%

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

Get started

Call Qwen3.5 2B 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/Qwen3.5-2B",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);