Does Wizardlm 2 8x22B support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Wizardlm 2 8x22B is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Wizardlm 2 8x22B hosted?

Wizardlm 2 8x22B runs on US hosting routes through the Opper gateway.

Is Wizardlm 2 8x22B trained on prompts and outputs?

No. Every hosting route for Wizardlm 2 8x22B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Wizardlm 2 8x22B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Wizardlm 2 8x22B. Contact hello@opper.ai to receive it.

Wizardlm 2 8x22B

by Microsoft

WizardLM-2 8x22B is an open-weight Mixture-of-Experts language model built on the Mixtral 8x22B architecture, released by Microsoft in April 2024. It uses 8 experts with 2 activated per token, achieving strong performance across instruction-following, multilingual tasks, reasoning, and agentic use cases. The model supports a 65,535 token context window and, per the official release, demonstrates highly competitive performance relative to leading proprietary models while outperforming existing open-source models at its scale. It is well-suited to chat, multilingual reasoning, code generation, and multi-step problem-solving. With its Mixture-of-Experts architecture, WizardLM-2 8x22B balances computational efficiency and capability for production deployment. The model is open-weight and available on Hugging Face, enabling integration into custom applications and fine-tuning.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

66K

Max output

Input price

$0.62 /1M

Output price

$0.62 /1M

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

Available routes

Wizardlm 2 8x22B 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
Novita	US	Enterprise	No	$0.62	$0.62

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

Data handling per route

Each route hosting Wizardlm 2 8x22B 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 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 Wizardlm 2 8x22B 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: "novita/microsoft/wizardlm-2-8x22b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);