When was Qwen3.5 9B released?

Alibaba released Qwen3.5 9B on 2 Mar 2026. It is available through the Opper gateway.

Does Qwen3.5 9B support zero data retention?

Yes. Qwen3.5 9B is available with zero data retention on DeepInfra, EmpirioLabs, Greenference, Regolo through the Opper gateway.

Where is Qwen3.5 9B hosted?

Qwen3.5 9B runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Qwen3.5 9B trained on prompts and outputs?

No. Every hosting route for Qwen3.5 9B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3.5 9B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3.5 9B. Contact hello@opper.ai to receive it.

Qwen3.5 9B

by Alibaba

Released 6 days after Qwen3.5 122B A10B · All Alibaba releases

Qwen3.5 9B is a 9 billion parameter multimodal model with a unified vision-language foundation trained with early fusion on multimodal tokens, combining Gated DeltaNet and Mixture-of-Experts layers 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 82.5, GPQA Diamond 81.7, and MMBench 90.1, covering reasoning and vision understanding. It runs in thinking mode by default for internal reasoning. With robust tool calling and a balanced performance-to-efficiency profile, it handles text, image, and video understanding across more than 200 languages and works well for agentic production deployments.

Call Qwen3.5 9B on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.10 /1M

Output price

$0.15 /1M

Released

2 Mar 2026

Web search

Via Opper

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

Available routes

Qwen3.5 9B runs on 4 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Greenference and Regolo (Italy). See every Qwen model hosted in the EU. One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.

Provider	Region	Training	Input	Output	Cache read
DeepInfra	US	No	$0.10	$0.15	Input price
EmpirioLabs	Multi	No	$0.09	$0.13	$0.04	Not offered on this route	Not offered on this route
Greenference	EU	No	$0.04	$0.07	$0.02	Not offered on this route	Not offered on this route
Regolo	EU	No	$0.08	$0.39	Input price	Not offered on this route	Not offered on this route

Live routes and prices as JSON: api.opper.ai/v3/models?q=qwen3.5-9b

Uptime and availability

One of Qwen3.5 9B's 4 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

99.86%route uptime, last 30 days

Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 3 further routes are not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Qwen3.5 9B 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: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; 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
GDPR DPA: DPA available
Transfer mechanism: SCCs

EmpirioLabs — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs; 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: On by default, keeps nothing
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: SCCs

Greenference — EU🇪🇺

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

Regolo — Italy🇮🇹

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
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Best for

Where Qwen3.5 9B ranks among the models on Opper with a score for each use case.

Agents0.8

Terminal-Bench 4.0 and AutomationBenchSee the Agents ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#206 of 505 LLMs

TierEfficient

Output speed57 tok/s

Intelligence Index (previous version)13.3

Coding

Terminal-Bench 4.0

SciCode

30%

Agentic & knowledge work

AutomationBench

GDPval

GDP.pdf

Briefcase (Elo)341

Terminal-Bench Hard

24%

τ²-Bench Telecom

87%

Science & reasoning

HLE Diamond

Humanity's Last Exam

15%

GPQA Diamond

81%

Long-context reasoning

70%

Knowledge

MMMU-Pro

69%

Math & instruction following

IFBench

67%

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

Get started

Call Qwen3.5 9B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen3.5 9B 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: "qwen3.5-9b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);