Does Qwen2.5 72B Instruct support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Qwen2.5 72B Instruct is available on request via Opper Enterprise — contact hello@opper.click.

Where is Qwen2.5 72B Instruct hosted?

Qwen2.5 72B Instruct runs on US hosting routes through the Opper gateway.

Is Qwen2.5 72B Instruct trained on prompts and outputs?

No. Every hosting route for Qwen2.5 72B Instruct is configured so customer prompts and outputs are not used to train models by default.

Qwen2.5 72B Instruct

by Alibaba

Qwen2.5 72B Instruct is Alibaba's September 2024 general-purpose model, trained on roughly 18 trillion tokens. It reports an MMLU around 86 and an 86.6 on HumanEval, with specialized training that strengthens its mathematics and coding ability across the full parameter scale. Native function calling, tool use, and structured JSON output make it well suited to agentic systems, API integration, and multi-step reasoning, and its Apache 2.0 weights allow custom fine-tuning and on-premise deployment. It is multilingual across more than 29 languages with a 32K context window, positioning it as a capable open alternative for teams prioritizing code quality and mathematical accuracy.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

33K

Max output

33K

Input price

$0.36 /1M

Output price

$0.40 /1M

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

Available routes

Qwen2.5 72B Instruct 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
DeepInfra	US	Enterprise	No	$0.36	$0.40

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

Data handling per route

Each route hosting Qwen2.5 72B Instruct 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 is available via Opper Enterprise contract. No training on customer data. US; unknown.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Limited debug logs
Third-party access: None disclosed
GDPR DPA: No DPA
Transfer mechanism: unknown

Benchmarks

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

Global rank#334 of 534 LLMs

TierEfficient

Output speed0 tok/s

First token0.00s

Intelligence Index9.6

Math Index14.0

Reasoning & knowledge

MMLU-Pro

72%

GPQA Diamond

49%

Humanity's Last Exam

Long-context reasoning

20%

Coding

LiveCodeBench

28%

SciCode

27%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

35%

Math & instruction following

AIME 2025

14%

IFBench

37%

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

Get started

Call Qwen2.5 72B Instruct 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: "deepinfra/Qwen/Qwen2.5-72B-Instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);