Does Llama 3.3 70B Instruct support zero data retention?

Yes. Llama 3.3 70B Instruct is available with zero data retention on evroc through the Opper gateway.

Where is Llama 3.3 70B Instruct hosted?

Llama 3.3 70B Instruct runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Llama 3.3 70B Instruct trained on prompts and outputs?

No. Every hosting route for Llama 3.3 70B Instruct is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Llama 3.3 70B Instruct?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Llama 3.3 70B Instruct. Contact hello@opper.ai to receive it.

Llama 3.3 70B Instruct

by Meta

Meta released Llama 3.3 70B Instruct in December 2024, an instruction-tuned dense model of 70 billion parameters that came close to the much larger Llama 3.1 405B on many benchmarks while remaining practical to serve. This entry is the FP8-quantized build, which stores the network in 8-bit floating point precision, roughly halving memory use and raising throughput while keeping output quality nearly indistinguishable from the 16-bit original. Instruction following, tool calling, structured output, and coverage of eight officially supported languages carry over unchanged, along with the 128K context window. The FP8 form suits high-volume production serving, chat backends, summarization, and agent loops where latency and efficiency matter as much as raw capability.

Call Llama 3.3 70B Instruct on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

128K

Max output

Input price

$1.14 /1M

Output price

$1.14 /1M

EU residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Llama 3.3 70B Instruct runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
evroc	EU		No	$1.14	$1.14	Input price

Data handling per route

Each route hosting Llama 3.3 70B Instruct has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

evroc — Sweden🇸🇪

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Llama 3.3 70B Instruct through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Llama 3.3 70B Instruct is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex 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: "evroc/llama-3.3-70b-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);