HostYourAI
Product
EU RouterDecision models like JevHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Earn with your GPU
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.3Kimi K2.7 CodeQwen3.5 397BLlama 3.3 70BMistralMiniMax M3All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAICompare costs
Resources
DocumentationSavings checkGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalogNewsSecurityFAQ
Pricing News
NL EN DE
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

DeepSeek V4 Flash

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

Note: DeepSeek-V4-Flash-DSpark is not a new model. It is the same checkpoint with an additional speculative decoding module attached. A minimal inference example is available in the inference folder. For more details, refer to: https://github.com/deepseek-ai/DeepSpec

Start for free ← All models
deepseek-ai/DeepSeek-V4-Flash-DSpark vLLM ready
text->text · deepseek-ai · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
—
Parameters
1,049K
Context window
201GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Context window 1,048,576 tokens
Minimum VRAM 201 GB
Architecture DeepseekV4ForCausalLM (vLLM)
License open-weights
Modality text->text
Released June 2026
Publisher deepseek-ai ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Prefer per token on the shared router? This model runs always-on as DeepSeek V4 Flash.
Dedicated GPU · per hour
from €10,95 per hour
Your own vLLM instance on European cloud (201 GB VRAM), billed hourly.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

✓ Verified working on 22-07-2026, responded in 61260 ms on our EU infrastructure.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

75.5 / 100 · Via LiveBench

Translated from its LiveBench result onto the same scale.

Range 69.2 to 81.8

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 04-10-2026

LiveBench · 74.2 · Rank 42 of 66
Reasoning 86.6
Coding 75.0
Agentic coding 46.8
Mathematics 86.8
Data analysis 79.3
Language 79.2
Instruction following 65.5
LiveBench · All tasks
Reasoning
theory of mind 86.5
zebra puzzle 100.0
spatial 90.0
logic with navigation 70.0
Coding
code generation 76.1
code completion 73.9
Agentic coding
javascript 63.6
typescript 26.7
python 50.0
Mathematics
AMPS Hard 97.0
integrals with game 65.0
math comp 96.1
olympiad 89.1
Data analysis
consecutive events 89.4
tablejoin 48.5
tablereformat 100.0
Language
connections 97.3
plot unscrambling 58.2
typos 82.0
Instruction following
paraphrase 61.7
simplify 58.4
story generation 70.5
summarize 71.5

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Flash-DSpark",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run DeepSeek V4 Flash in the EU?

Yes. HostYourAI runs DeepSeek V4 Flash on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting DeepSeek V4 Flash GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does DeepSeek V4 Flash cost?

DeepSeek V4 Flash is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per hour. Tell us your use case and we will set it up for you.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from DeepSeek

DeepSeek V4.1 Flash

We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.

763B 1M context View model →
DeepSeek V4 Flash Vision Exp

We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

305B 1M context View model →
DeepSeek V4 Pro 0813

DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.

1650B 1M context View model →
DeepSeek V4 Pro

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.

1M context View model →
DeepSeek V4 Flash

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.

291B 1M context View model →
DeepSeek OCR 2

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8：

3.4B 8K context View model →

Try DeepSeek V4 Flash for free

Creating an account takes a minute. Test DeepSeek V4 Flash straight away in the playground.

Start for free