Does Llama 3.2 1B Instruct support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Llama 3.2 1B Instruct is available on request via Opper Enterprise — contact hello@opper.click.

Where is Llama 3.2 1B Instruct hosted?

Llama 3.2 1B Instruct runs on US hosting routes through the Opper gateway.

Is Llama 3.2 1B Instruct trained on prompts and outputs?

No. Every hosting route for Llama 3.2 1B Instruct is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Llama 3.2 1B Instruct?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Llama 3.2 1B Instruct. Contact hello@opper.click to receive it.

Llama 3.2 1B Instruct

by Meta

Llama 3.2 1B Instruct is Meta's ultra-compact model, released September 2024 and tuned for on-device, mobile, and embedded use where memory and compute are limited. With 1 billion parameters and a 131,000-token context window, it suits local-first inference without cloud dependencies. Despite its small size, the model supports structured output generation, enabling programmatic extraction and JSON formatting for downstream automation. It handles classification, sentiment analysis, intent detection, and simple text generation on modest hardware. Its open-weight design enables on-device fine-tuning and adaptation to specific tasks without connectivity. It is well suited to local applications, embedded systems, and mobile apps, and is often combined with retrieval augmentation to extend capability without scaling parameters.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

32K

Input price

$0.02 /1M

Output price

$0.02 /1M

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

Available routes

Llama 3.2 1B 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
Novita	US	Enterprise	No	$0.02	$0.02

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

Data handling per route

Each route hosting Llama 3.2 1B Instruct 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 Llama 3.2 1B 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: "novita/meta-llama/llama-3.2-1b-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);