Does Qwen3.5 27B support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen3.5 27B is available on request via Opper Enterprise — contact hello@opper.click.

Where is Qwen3.5 27B hosted?

Qwen3.5 27B runs on US hosting routes through the Opper gateway.

Is Qwen3.5 27B trained on prompts and outputs?

No. Every hosting route for Qwen3.5 27B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3.5 27B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3.5 27B. Contact hello@opper.click to receive it.

Qwen3.5 27B

by Alibaba

Qwen3.5-27B is a 27 billion parameter multimodal model that blends vision and language through early fusion training on multimodal tokens, built on a hybrid architecture of Gated DeltaNet and Mixture-of-Experts layers. It supports a 262,144 token native context window, extensible toward roughly one million tokens with YaRN scaling. Reported scores include MMLU-Pro 86.1, GPQA Diamond 85.5, SWE-bench Verified 72.4, and MathVista 86.0, reflecting balanced strength across reasoning, coding, and visual understanding. It runs in thinking mode by default, generating reasoning before responses. The model handles text, image, and video inputs across more than 200 languages, suiting knowledge-intensive problems, agentic coding, and multimodal reasoning.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.26 /1M

Output price

$2.60 /1M

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

Available routes

Qwen3.5 27B runs on 2 different routes 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	$0.26	$2.60
Novita	US	Enterprise	No	$0.30	$2.40

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

Data handling per route

Each route hosting Qwen3.5 27B 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

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#73 of 534 LLMs

TierStrong

Output speed83 tok/s

First token1.41s

Intelligence Index33.8

Reasoning & knowledge

GPQA Diamond

86%

Humanity's Last Exam

22%

Long-context reasoning

67%

Coding

SciCode

40%

Agentic & tool use

Terminal-Bench Hard

33%

τ²-Bench Telecom

94%

Math & instruction following

IFBench

76%

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

Get started

Call Qwen3.5 27B 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/Qwen3.5-27B",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);