Does DeepSeek V4 Flash (0731) Fast support zero data retention?

Yes. DeepSeek V4 Flash (0731) Fast is available with zero data retention by default on Wafer through the Opper gateway.

Where is DeepSeek V4 Flash (0731) Fast hosted?

DeepSeek V4 Flash (0731) Fast runs on US hosting routes through the Opper gateway.

Is DeepSeek V4 Flash (0731) Fast trained on prompts and outputs?

No. Every hosting route for DeepSeek V4 Flash (0731) Fast is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for DeepSeek V4 Flash (0731) Fast?

Yes. A GDPR Data Processing Agreement is available on at least one route serving DeepSeek V4 Flash (0731) Fast. Contact hello@opper.ai to receive it.

DeepSeek V4 Flash (0731) Fast

by DeepSeek

DeepSeek V4 Flash 0731 Fast serves the DeepSeek-V4-Flash-0731 checkpoint through a speed-optimized path. The model underneath is unchanged, a lightweight 284 billion parameter sparse MoE with 13 billion active parameters per token and a one-million-token context window, whose July 2026 retraining brought large agentic and coding gains over the original V4 Flash release. It keeps the three reasoning modes (non-think, think-high, think-max) and the XML-based tool-call format that preserves reasoning content across tool-call boundaries, so it drops into an existing V4 Flash integration without code changes. Even on the premium serving tier this stays among the cheaper capable agentic models on the platform, which is rather the point. It suits high-volume tool-calling loops and interactive agents where latency and unit cost both matter, rather than batch work that can wait on the standard tier.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

—

Input price

$0.10 /1M

Output price

$0.25 /1M

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

Available routes

DeepSeek V4 Flash (0731) Fast 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
Wafer	US	Zero data retention	No	$0.10	$0.25

Data handling per route

Each route hosting DeepSeek V4 Flash (0731) Fast has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Wafer — United States🇺🇸

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

Zero data retention: On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: None
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call DeepSeek V4 Flash (0731) Fast 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 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: "wafer/deepseek-v4-flash-0731-fast",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);