Does Qwen 3.5 397B A17B Fast support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen 3.5 397B A17B Fast is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Qwen 3.5 397B A17B Fast hosted?

Qwen 3.5 397B A17B Fast runs on US hosting routes through the Opper gateway.

Is Qwen 3.5 397B A17B Fast trained on prompts and outputs?

No. Every hosting route for Qwen 3.5 397B A17B Fast is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen 3.5 397B A17B Fast?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen 3.5 397B A17B Fast. Contact hello@opper.ai to receive it.

Qwen 3.5 397B A17B Fast

by Alibaba

Qwen3.5 397B A17B Fast is a speed-optimized serving variant of the 397B A17B sparse Mixture-of-Experts model, tuned for lower latency while keeping the same reasoning and coding capabilities. It shares the 397 billion total parameter, 17 billion active per token design and the 262,144 token native context window, extensible toward roughly one million tokens with YaRN scaling. Reported scores match the base model, including MMLU-Pro 87.8 and SWE-bench Verified 76.4. It runs in thinking mode by default and is multimodal across text, image, and video. The faster token generation makes it a fit for interactive agentic applications that need quick responses while still supporting tool calling, structured outputs, and complex problem solving across more than 200 languages.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

66K

Input price

$0.60 /1M

Output price

$3.60 /1M

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

Available routes

Qwen 3.5 397B A17B 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	$0.60	$3.60

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

Data handling per route

Each route hosting Qwen 3.5 397B A17B 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 3.5 397B A17B 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/qwen3.5-397b-a17b-fast",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);