Model garden Router · warm Dedicated · available

DeepSeek R1 0528

Instantly via the EU router or as a dedicated GPU deployment. Data stays in Europe.

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introdu...

deepseek-ai/DeepSeek-R1-0528
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
164K
Context window
827GB
Minimum VRAM
POST /api/v1/chat/completions 200 OK

Specifications

Context window 164,000 tokens
Minimum VRAM 827 GB
Architecture DeepseekV3ForCausalLM (vLLM)
License open-weights
Modality text->text
Released May 2025
Publisher deepseek-ai ↗

Pricing

Shared router · per token
€0.76
Input (per 1M tokens)
€2.99
Output (per 1M tokens)
€0.20 per million cached input tokens
Dedicated GPU · per hour
from €54,00 per hour
Your own vLLM instance on European cloud (827 GB VRAM), billed hourly.

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

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.

64.1 / 100 · Measured

Measured by Epoch AI across 12 benchmarks, with a range.

Range 60.8 to 66.0 · Rank 111 of 274 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 08-10-2026

LiveBench · 69.4
Reasoning 91.1
Coding 73.2
Agentic coding 20.0
Mathematics 85.3
Data analysis 71.5
Language 64.8
Instruction following 80.0
Every benchmark (12)
MATH level 5 96.6
Lech Mazur Writing 81.9
Fiction.LiveBench 75.0
Aider polyglot 71.4
GPQA diamond 68.4
OTIS Mock AIME 2024-2025 66.4
METR Time Horizons 53.8
WeirdML 41.6
DeepResearch Bench 35.1
SimpleBench 29.0
ARC-AGI 21.2
ARC-AGI-2 1.1
LiveBench · All tasks
Reasoning
web of lies v3 96.0
zebra puzzle 85.3
spatial 92.0
Coding
code generation 74.7
code completion 71.7
Agentic coding
javascript 15.0
typescript 15.0
python 30.0
Mathematics
AMPS Hard 86.0
math comp 91.7
olympiad 78.1
Data analysis
tablejoin 43.1
tablereformat 100.0
Language
connections 87.5
plot unscrambling 47.0
typos 60.0
Instruction following
paraphrase 82.0
simplify 79.3
story generation 81.3
summarize 77.3

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-R1-0528",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run DeepSeek R1 0528 in the EU?

Yes. HostYourAI runs DeepSeek R1 0528 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 R1 0528 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 R1 0528 cost?

Via the shared EU router you pay €0.76 per million input tokens and €2.99 per million output tokens, with no fixed costs. For high volume or isolation you can also run DeepSeek R1 0528 as a dedicated hourly GPU instance.

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 R1 0528 for free

Creating an account takes a minute. Test DeepSeek R1 0528 straight away in the playground.

Start for free