Does DeepSeek V4 Flash support zero data retention?

Yes. DeepSeek V4 Flash is available with zero data retention by default on Alibaba Cloud, DeepInfra, Fireworks, Geodd, Novita through the Opper gateway.

Where is DeepSeek V4 Flash hosted?

DeepSeek V4 Flash runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is DeepSeek V4 Flash trained on prompts and outputs?

No. Every hosting route for DeepSeek V4 Flash is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for DeepSeek V4 Flash?

Yes. A GDPR Data Processing Agreement is available on at least one route serving DeepSeek V4 Flash. Contact hello@opper.ai to receive it.

DeepSeek V4 Flash

by DeepSeek

DeepSeek-V4-Flash, released April 2026, is a lightweight 284-billion-parameter sparse MoE with just 13 billion active parameters per token, supporting a one-million-token context window. It reaches roughly 10% of the inference FLOPs and 7% of the KV-cache memory of V3.2, using a hybrid of Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) for efficient long context. The model offers three reasoning modes, non-think, think-high, and think-max, plus a dedicated XML-based tool-call format that preserves reasoning content across tool-call boundaries for cleaner agentic loops. Its reasoning quality is reported to approach the larger V4-Pro on many tasks. Open-sourced under an MIT license with weights on Hugging Face, V4-Flash targets cost-conscious teams deploying long-context reasoning agents that need affordable million-token inference.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

393K

Input price

$0.14 /1M

Output price

$0.28 /1M

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

Available routes

DeepSeek V4 Flash runs on 5 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
Alibaba Cloud	EU	Enterprise	No	$0.14	$0.28
DeepInfra	US	Enterprise	No	$0.14	$0.28
Fireworks	US	Enterprise	No	$0.14	$0.28
Geodd	US	Zero data retention	No	$0.14	$0.30
Novita	US	Enterprise	No	$0.14	$0.28

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

Data handling per route

Each route hosting DeepSeek V4 Flash has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Alibaba Cloud — Germany🇩🇪

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; 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: Not applicable — data stays in EU

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

Fireworks — 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: None
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: SCCs

Geodd — United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs.

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: None
Third-party access: Provider may share with subprocessors / partners
GDPR DPA: No DPA
Transfer mechanism: SCCs

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#27 of 531 LLMs

TierStrong

Output speed110 tok/s

First token1.00s

Intelligence Index40.3

Coding Index38.7

Reasoning & knowledge

GPQA Diamond

89%

Humanity's Last Exam

32%

Long-context reasoning

63%

Coding

SciCode

45%

Agentic & tool use

Terminal-Bench Hard

36%

τ²-Bench Telecom

95%

Math & instruction following

IFBench

79%

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

Get started

Call DeepSeek V4 Flash 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.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "alibaba:eu/deepseek-v4-flash",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);