Does Qwen3.7-Max support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen3.7-Max is available on request via Opper Enterprise — contact hello@opper.click.

Where is Qwen3.7-Max hosted?

Qwen3.7-Max runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Qwen3.7-Max trained on prompts and outputs?

No. Every hosting route for Qwen3.7-Max is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Qwen3.7-Max?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Qwen3.7-Max. Contact hello@opper.click to receive it.

Qwen3.7-Max

by Alibaba

Qwen3.7-Max is Alibaba's flagship proprietary reasoning model, designed for extended multi-step agent tasks. It features a 1 million token context window and generates internal reasoning chains before committing to final answers, scoring 56.6 on the Artificial Analysis Intelligence Index, the highest placement for a Chinese model at its release. Specialized for autonomous code work, tool orchestration, and long-horizon tasks, the model was demonstrated optimizing an attention kernel autonomously over roughly 35 hours and more than a thousand tool calls. It excels at iterative tool use and self-correction, making it well suited to agentic applications. Text-only interface with tool calling, structured output, and deep reasoning capabilities. Proprietary and closed-weight, with measured improvements in factual reliability over its predecessor.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

66K

Input price

$1.65 /1M

Output price

$4.95 /1M

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

Available routes

Qwen3.7-Max 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
Alibaba Cloud	EU	Enterprise	No	$1.65	$4.95
Novita	US	Enterprise	No	$1.25	$3.75

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

Data handling per route

Each route hosting Qwen3.7-Max has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Alibaba Cloud — Germany🇩🇪

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; 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: Not applicable — data stays in EU

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#12 of 534 LLMs

TierStrong

Output speed196 tok/s

First token1.59s

Intelligence Index46.0

Coding Index66.0

Reasoning & knowledge

GPQA Diamond

92%

Humanity's Last Exam

38%

Long-context reasoning

69%

Coding

SciCode

49%

Agentic & tool use

Terminal-Bench Hard

51%

τ²-Bench Telecom

95%

Math & instruction following

IFBench

81%

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

Get started

Call Qwen3.7-Max 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: "alibaba:eu/qwen3.7-max",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);