Does Qwen 3 235B A22B Thinking Fast support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen 3 235B A22B Thinking Fast is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Qwen 3 235B A22B Thinking Fast hosted?

Qwen 3 235B A22B Thinking Fast runs on US hosting routes through the Opper gateway.

Is Qwen 3 235B A22B Thinking Fast trained on prompts and outputs?

No. Every hosting route for Qwen 3 235B A22B Thinking Fast is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen 3 235B A22B Thinking Fast?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen 3 235B A22B Thinking Fast. Contact hello@opper.ai to receive it.

Qwen 3 235B A22B Thinking Fast

by Alibaba

Qwen3-235B-A22B-Thinking-2507-Fast is a faster-inference build of the 235B Thinking 2507 reasoning model, tuned for higher throughput while keeping its reasoning behavior. It activates 22 billion parameters from a 235 billion total pool and runs in thinking mode for step-by-step problem solving. The model retains the reasoning strengths of the standard Thinking variant across mathematical, logical, and coding tasks, and supports a 262K context window for long-form reasoning and document understanding, with 100+ language coverage inherited from the base family. Tool calling enables integration into agentic workflows. As part of the Qwen3 MoE family, it activates only 22B of its 235B parameters per forward pass for computational efficiency. Open-weight under Apache 2.0.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

66K

Input price

$0.50 /1M

Output price

$2.00 /1M

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

Available routes

Qwen 3 235B A22B Thinking Fast 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
Nebius	US	Enterprise	No	$0.50	$2.00

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

Data handling per route

Each route hosting Qwen 3 235B A22B Thinking Fast has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Nebius — 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

Get started

Call Qwen 3 235B A22B Thinking Fast 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.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "nebius/qwen3-235b-a22b-thinking-2507-fast",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);