Does DeepSeek V4 Flash Vision support zero data retention?

Yes. DeepSeek V4 Flash Vision is available with zero data retention on DeepInfra through the Opper gateway.

Where is DeepSeek V4 Flash Vision hosted?

DeepSeek V4 Flash Vision runs on US hosting routes through the Opper gateway.

Is DeepSeek V4 Flash Vision trained on prompts and outputs?

Training behaviour varies by route. See the per-route data-handling section for each provider's training posture.

Is a GDPR DPA available for DeepSeek V4 Flash Vision?

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

DeepSeek V4 Flash Vision

by DeepSeek

DeepSeek-V4-Flash-Vision-Exp, announced on August 21, 2026 with open weights following at the end of that month, is DeepSeek's first experimental multimodal model in the V4 family. It extends the DeepSeek-V4-Flash architecture, a sparse mixture-of-experts with 13 billion active parameters, with visual modules added through continued training, bringing the checkpoint to about 305 billion parameters. It keeps the Flash line's selectable reasoning effort, works across a context window of up to one million tokens, and accepts mixed text and image input. On the text side DeepSeek says it holds level with V4 Flash, from agent tasks and reasoning to world knowledge, with 83.9 on Terminal-Bench 2.1 and 59.3 on DeepSWE, while the multimodal agent benchmarks jump to what the company places close to Claude Opus 4.8: 36.5 on ApexBench, 64.3 on Chartography, and 35.0 on ZeroBench at pass@5. Chart and document understanding, screenshot-driven agents, and workflows that interleave text and images are the natural fits. The weights are open under the MIT license. DeepSeek followed it in September 2026 with V4.1 Flash, which builds visual understanding in from the start and has superseded the experimental build in DeepSeek's own lineup.

Call DeepSeek V4 Flash Vision 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

Max output

393K

Input price

$0.44 /1M$0.01 cache read

Output price

$1.32 /1M

US residency available
Zero data retention on pay-as-you-go
GDPR DPA available

Available routes

DeepSeek V4 Flash Vision runs on 2 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. One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
DeepInfra	US		No	$0.44	$1.32	$0.01
DeepSeek	China		Yes	$0.44	$1.32	$0.01	Not offered on this route	Not offered on this route

Live routes and prices as JSON: api.opper.ai/v3/models?q=deepseek-v4-flash-vision-exp

Uptime and availability

One of DeepSeek V4 Flash Vision's 2 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. 1 further route is not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting DeepSeek V4 Flash Vision 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: 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: No classifier
GDPR DPA: DPA available
Transfer mechanism: unknown

DeepSeek — China🇨🇳

Content is retained: used for training by default. Trained on customer data by default. CN.

Zero data retention: Retained: used for training by default.
Training: Trained on customer data by default.
Logging: Other
Abuse monitoring: Always on, holds flagged content, stored in China, a person can view samples
Caching: Content cached for replay
GDPR DPA: No DPA
Transfer mechanism: Not applicable

Get started

Call DeepSeek V4 Flash Vision through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

DeepSeek V4 Flash Vision 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: "deepseek-v4-flash-vision-exp",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);