Does DeepSeek V3 support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for DeepSeek V3 is available on request via Opper Enterprise — contact hello@opper.click.

Where is DeepSeek V3 hosted?

DeepSeek V3 runs on US hosting routes through the Opper gateway.

Is DeepSeek V3 trained on prompts and outputs?

No. Every hosting route for DeepSeek V3 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for DeepSeek V3?

Yes. A GDPR Data Processing Agreement is available on at least one route serving DeepSeek V3. Contact hello@opper.click to receive it.

DeepSeek V3

by DeepSeek

DeepSeek-V3 is a 671-billion-parameter open-weight Mixture-of-Experts model released in December 2024 that activates just 37 billion parameters per token for efficient inference. It pairs Multi-head Latent Attention with sparse expert routing to deliver strong reasoning, mathematics, and code generation. The model was trained on 14.8 trillion tokens for roughly 5.6 million dollars in compute, a fraction of what comparable closed models reportedly required. It supports function calling and tool use, making it a practical base for production agentic workflows. DeepSeek-V3 targets cost-conscious teams that want capable general-purpose performance without proprietary lock-in, and its architecture became the foundation for the wider V3 family of releases.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

164K

Max output

164K

Input price

$0.32 /1M

Output price

$0.89 /1M

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

Available routes

DeepSeek V3 runs on 2 different routes 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	$0.32	$0.89
Novita	US	Enterprise	No	$0.89	$0.89

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

Data handling per route

Each route hosting DeepSeek V3 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

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

Benchmarks

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

Global rank#318 of 534 LLMs

TierEfficient

Output speed0 tok/s

First token0.00s

Intelligence Index10.4

Math Index26.0

Reasoning & knowledge

MMLU-Pro

75%

GPQA Diamond

56%

Humanity's Last Exam

Long-context reasoning

29%

Coding

LiveCodeBench

36%

SciCode

35%

Agentic & tool use

Terminal-Bench Hard

τ²-Bench Telecom

23%

Math & instruction following

AIME 2025

26%

IFBench

35%

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

Get started

Call DeepSeek V3 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/deepseek-ai/DeepSeek-V3",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);