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.

Call DeepSeek V4 Flash on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Key info

Input
Output
Features
Context window
1M
Max output
393K
Input price
$0.15 /1M$0.03 cache read
Output price
$0.30 /1M
  • EU residency available
  • US residency available
  • Zero data retention on pay-as-you-go
  • GDPR DPA available

Available routes

DeepSeek V4 Flash runs on 11 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.

ProviderRegionZero data retentionTrainingInputOutputCache read
MultiNo$0.15$0.30$0.03
Multi—Not established—$0.14$0.28$0.03
MultiNo$0.14$0.28$0.03
USNo$0.09$0.18$0.02
USNo$0.07$0.17$0.02
USNo$0.14$0.30Input price
USNo$0.12$0.35$0.03
EUNo$0.14$0.28$0.03
USNo$0.14$0.28$0.03
EUNo$0.28$0.56$0.07
EUNo$0.25$0.30$0.06

Uptime and availability

DeepSeek V4 Flash runs on 3 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days
Averaged across these routes on their own, a single provider reached 100% over the same window.
Daily status through the gateway, which serves each request from whichever route is healthy.
3 monitored providers serve DeepSeek V4 Flash.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 8 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.

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 — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
SCCs

Baidu Qianfan — China🇨🇳

Zero data retention posture is not established for this route. Training posture pending review. GLOBAL; unknown.

Zero data retention
Not established.
GDPR DPA
No DPA
Transfer mechanism
unknown

BytePlus — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 180 days for abuse monitoring only, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
With abuse monitoring, 180-day window.
Training
No training on customer data.
Logging
Abuse monitoring (180-day retention)
Abuse monitoring
On by default, holds flagged content, 180 days, stored in Malaysia, a person can view samples
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
SCCs

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

DigitalOcean — United States🇺🇸

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. US; dpf sccs; DPA available.

Zero data retention
With abuse monitoring, flagged content held.
Training
No training on customer data.
Logging
None
Abuse monitoring
Always on, holds flagged content, stored in United States
Caching
Content cached for replay
Subprocessor access
No subprocessor reads content
GDPR DPA
DPA available
Transfer mechanism
dpf sccs

Geodd — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; 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
Caching
Not cached
GDPR DPA
DPA available
Transfer mechanism
SCCs

Morph — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention
With abuse monitoring, 30-day window.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Abuse monitoring
On by default, holds flagged content, a person can view samples
GDPR DPA
DPA available
Transfer mechanism
SCCs

Nextbit — Spain🇪🇸

Content is retained: provider logging, 90-day retention. No training on customer data. EU; SCCs; DPA available.

Zero data retention
Retained: provider logging, 90-day retention.
Training
No training on customer data.
Logging
Other (90-day retention)
Abuse monitoring
On by default, holds flagged content
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
SCCs

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; 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
On by default, keeps nothing
GDPR DPA
DPA available
Transfer mechanism
SCCs

Sference — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EEA; SCCs; 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
Caching
Content cached for replay
Subprocessor access
No subprocessor reads content
GDPR DPA
DPA available
Transfer mechanism
SCCs

TensorX — European Union🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; 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
Caching
Content cached for replay
GDPR DPA
DPA available
Transfer mechanism
Not applicable — data stays in EU

Benchmarks

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

Global rank#66 of 664 LLMs
TierStrong
Output speed232 tok/s
First token0.75s
Intelligence Index34.8
Coding Index65.0
Reasoning & knowledge
GPQA Diamond
91%
Humanity's Last Exam
35%
Long-context reasoning
81%
Coding
SciCode
50%

Get started

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

DeepSeek V4 Flash 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

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "deepseek-v4-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare DeepSeek V4 Flash with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from DeepSeek

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation