When was Qwen3.5 122B A10B released?

Alibaba released Qwen3.5 122B A10B on 24 Feb 2026. It is available through the Opper gateway.

Does Qwen3.5 122B A10B support zero data retention?

Yes. Qwen3.5 122B A10B is available with zero data retention on Novita, Regolo through the Opper gateway.

Where is Qwen3.5 122B A10B hosted?

Qwen3.5 122B A10B runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Qwen3.5 122B A10B trained on prompts and outputs?

No. Every hosting route for Qwen3.5 122B A10B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3.5 122B A10B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3.5 122B A10B. Contact hello@opper.ai to receive it.

Qwen3.5 122B A10B

by Alibaba

All Alibaba releases

Qwen3.5-122B-A10B is Alibaba's multimodal foundation model that combines text, image, and video understanding using a hybrid architecture of Gated DeltaNet layers and a sparse Mixture-of-Experts. It carries 122 billion total parameters with 10 billion activated per token, keeping inference efficient while sustaining strong performance across reasoning, coding, and vision tasks. The model has a 262,144 token native context window, extensible toward roughly one million tokens with YaRN scaling, and runs in thinking mode by default, producing internal reasoning before its final answer. It supports tool calling and structured outputs across more than 200 languages. This makes it a fit for complex agentic workflows that need function calling, multi-step reasoning, and structured responses over text and visual inputs.

Call Qwen3.5 122B A10B 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

66K

Input price

$0.40 /1M

Output price

$3.20 /1M

Released

24 Feb 2026

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 122B A10B runs on 2 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 Regolo (Italy). See every Qwen model hosted in the EU.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Novita	US		No	$0.40	$3.20	Input price
Regolo	EU		No	$1.12	$4.71	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=qwen3.5-122b-a10b

Uptime and availability

One of Qwen3.5 122B A10B's 2 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

100%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. 1 further route is not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Qwen3.5 122B A10B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Novita — 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: On by default, keeps nothing
GDPR DPA: DPA available
Transfer mechanism: SCCs

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

Benchmarks

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

Global rank#280 of 687 LLMs

TierEfficient

Output speed134 tok/s

First token1.00s

Intelligence Index15.6

Coding Index45.7

Reasoning & knowledge

GPQA Diamond

86%

Humanity's Last Exam

25%

Long-context reasoning

76%

Coding

SciCode

40%

Agentic & tool use

Terminal-Bench Hard

31%

τ²-Bench Telecom

94%

Math & instruction following

IFBench

76%

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

Get started

Call Qwen3.5 122B A10B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen3.5 122B A10B 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: "qwen3.5-122b-a10b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);