When was Llama 3.3 70B released?

Meta released Llama 3.3 70B on 6 Dec 2024. It is available through the Opper gateway.

Does Llama 3.3 70B support zero data retention?

Yes. Llama 3.3 70B is available with zero data retention on GreenPT, Infercom, Novita, Regolo, SCX through the Opper gateway. Other routes carry zero data retention with abuse monitoring; see each route's window in the data-handling section.

Where is Llama 3.3 70B hosted?

Llama 3.3 70B runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Llama 3.3 70B trained on prompts and outputs?

No. Every hosting route for Llama 3.3 70B 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?

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

Llama 3.3 70B

by Meta

Released 72 days after Llama 3.2 11B Vision Instruct · All Meta releases

Llama 3.3 70B Instruct is Meta's refined large-scale model, released December 2024. With 70 billion parameters and a 65,536-token context window, it iterates on open-weight general-purpose language modeling, improving multilingual fluency, instruction adherence, and code understanding over earlier releases. The model supports tool calling and structured output for agentic workflows and programmatic integration. Its multilingual training officially spans eight languages, benefiting globally distributed teams and multi-language applications. It suits complex reasoning, long-form generation, code synthesis, and knowledge-intensive tasks where accuracy and depth matter. The open-weight release supports research fine-tuning and on-premise deployment, and it refines the 70B lineage with learnings carried over from the wider Llama family.

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

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

16K

Input price

$1.25 /1M

Output price

$1.25 /1M

Released

6 Dec 2024

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

Available routes

Llama 3.3 70B runs on 6 different routes 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	Training	Input	Output	Cache read
GreenPT	EU	No	$1.25	$1.25	Input price
Infercom	US	No	$0.68	$1.37	Input price
Novita	US	No	$0.14	$0.40	Input price
Regolo	EU	No	$0.68	$3.08	Input price
Scaleway	EU	No	$1.03	$1.03	Input price
SCX	US	No	$0.83	$2.66	Input price

Uptime and availability

One of Llama 3.3 70B's 6 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

100%route uptime, last 30 days

Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 5 further routes are not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

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

GreenPT — EU🇪🇺

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: Keeps nothing
Caching: Content cached for replay
Subprocessor access: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Infercom — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; 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: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: SCCs

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; 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: On by default, keeps nothing
GDPR DPA: DPA available
Transfer mechanism: SCCs

Regolo — Italy🇮🇹

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

Scaleway — France🇫🇷

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 14 days for abuse monitoring only, and are not used for training. No training on customer data. EU; DPA available.

Zero data retention: With abuse monitoring, 14-day window.
Training: No training on customer data.
Logging: Abuse monitoring (14-day retention)
Abuse monitoring: No classifier
Caching: Content cached for replay
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

SCX — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; 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: Optional (off by default), keeps nothing
GDPR DPA: DPA available
Transfer mechanism: unknown

Benchmarks

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

Global rank#463 of 665 LLMs

TierEfficient

Output speed93 tok/s

First token0.62s

Intelligence Index7.7

Coding Index11.9

Math Index7.7

Reasoning & knowledge

MMLU-Pro

71%

GPQA Diamond

50%

Humanity's Last Exam

Long-context reasoning

16%

Coding

LiveCodeBench

29%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

27%

Math & instruction following

AIME 2025

IFBench

47%

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

Get started

Call Llama 3.3 70B 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 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: "llama-3.3-70b-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);