Does Qwen3.5 35B A3B support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen3.5 35B A3B is available on request via Opper Enterprise — contact hello@opper.click.

Where is Qwen3.5 35B A3B hosted?

Qwen3.5 35B A3B runs on US hosting routes through the Opper gateway.

Is Qwen3.5 35B A3B trained on prompts and outputs?

No. Every hosting route for Qwen3.5 35B A3B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3.5 35B A3B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3.5 35B A3B. Contact hello@opper.click to receive it.

Qwen3.5 35B A3B

by Alibaba

Qwen3.5-35B-A3B is a vision-language model built on a sparse Mixture-of-Experts architecture with 35 billion total parameters and only 3 billion activated per token, pairing Gated DeltaNet layers with 256 experts (8 routed plus 1 shared) for efficient inference. It supports a 262,144 token native context window, extensible toward roughly one million tokens with YaRN scaling. Reported scores include MMLU-Pro 85.3, GPQA Diamond 84.2, MMMU-Pro 75.1, and MathVista 86.2, spanning reasoning, vision, and code generation. The model runs in thinking mode by default, producing reasoning traces before answers. It is a strong fit for agentic applications that combine tool calling, structured outputs, and complex problem solving over text, image, and video across more than 200 languages.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.14 /1M

Output price

$1.00 /1M

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

Available routes

Qwen3.5 35B A3B 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	$0.14	$1.00
Novita	US	Enterprise	No	$0.25	$2.00

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

Data handling per route

Each route hosting Qwen3.5 35B 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

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#112 of 534 LLMs

TierEfficient

Output speed165 tok/s

First token1.15s

Intelligence Index29.3

Reasoning & knowledge

GPQA Diamond

85%

Humanity's Last Exam

20%

Long-context reasoning

63%

Coding

SciCode

38%

Agentic & tool use

Terminal-Bench Hard

27%

τ²-Bench Telecom

89%

Math & instruction following

IFBench

73%

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

Get started

Call Qwen3.5 35B 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/Qwen3.5-35B-A3B",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);