Does Llama 3.1 8B Instruct Turbo support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Llama 3.1 8B Instruct Turbo is available on request via Opper Enterprise — contact hello@opper.click.

Where is Llama 3.1 8B Instruct Turbo hosted?

Llama 3.1 8B Instruct Turbo runs on US hosting routes through the Opper gateway.

Is Llama 3.1 8B Instruct Turbo trained on prompts and outputs?

No. Every hosting route for Llama 3.1 8B Instruct Turbo is configured so customer prompts and outputs are not used to train models by default.

Llama 3.1 8B Instruct Turbo

by Meta

Llama 3.1 8B Instruct Turbo is a throughput-optimized build of the standard 8B model. It keeps the full 131,072-token context window and tool calling support while favoring higher request capacity and efficient serving for systems handling large concurrent workloads. The optimization targets inference efficiency without changing the model's instruction-following or tool-use behavior. It suits high-traffic APIs and real-time services where both responsiveness and cost matter. It pairs well with batch inference and load-balancing strategies to amortize serving costs. The open-weight foundation permits self-hosting and fine-tuning when application-specific adjustments are needed alongside the speed-focused serving build.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

131K

Input price

$0.02 /1M

Output price

$0.03 /1M

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

Available routes

Llama 3.1 8B Instruct Turbo 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	$0.02	$0.03

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

Data handling per route

Each route hosting Llama 3.1 8B Instruct Turbo 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

Get started

Call Llama 3.1 8B Instruct Turbo 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/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);