Skip to content
03 Model garden Serve

DeepSeek V4 Pro 0813

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

curl
$ curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro-0813",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Call it now

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

Serve Model garden
deepseek-ai/DeepSeek-V4-Pro-0813

text->text · deepseek-ai · sovereign EU

Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain

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...

Router
Router · warm
Dedicated
Dedicated · available
Input (per 1M tokens)
€2.30
Output (per 1M tokens)
€4.60
1650BParameters
1,049KContext window
1072GBMinimum VRAM
POST /api/v1/chat/completions 200 OK

Specifications

Parameters1650B
Context window1,048,576 tokens
Minimum VRAM1072 GB
ArchitectureDeepseekV4ForCausalLM (vLLM)
Licensemit
Modalitytext->text
ReleasedAugust 2026
Publisherdeepseek-ai ↗

Pricing

Shared router · per token

€2.30Input (per 1M tokens)
€4.60Output (per 1M tokens)

€0.58 per million cached input tokens

Dedicated GPU · per hour

from €63,12 per hourYour own vLLM instance on European cloud (1072 GB VRAM), billed per minute.

Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, 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.

82.4 / 100 · Measured

Measured by Epoch AI across 16 benchmarks, with a range.

Range 80.1 to 85.0 · Rank 41 of 256 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 15-11-2026

LiveBench · 77.4 · Rank 24 of 70

Reasoning85.8
Coding77.2
Agentic coding55.0
Mathematics95.1
Data analysis79.2
Language82.1
Instruction following67.7
Every benchmark (16)
OTIS Mock AIME 2024-202598.6
GPQA diamond92.6
ARC-AGI90.5
DTBench89.8
FrontierMath-Tiers-1-3-v2-Private68.0
WeirdML66.2
ARC-AGI-261.3
LMCA53.5
SimpleQA Verified52.9
ProofBench50.0
APEX-Agents47.3
Chess Puzzles43.2
Mystery Game Puzzles37.2
MirrorCode33.3
FrontierCode28.5
FrontierMath-Tier-4-v2-Private26.8
LiveBench · All tasks
Reasoning
theory of mind84.6
zebra puzzle96.8
spatial96.0
logic with navigation66.0
Coding
code generation76.1
code completion78.3
Agentic coding
javascript68.2
typescript46.7
python50.0
Mathematics
AMPS Hard98.0
integrals with game94.0
math comp97.1
olympiad91.3
Data analysis
consecutive events90.2
tablejoin49.5
tablereformat98.0
Language
connections100.0
plot unscrambling64.2
typos82.0
Instruction following
paraphrase68.6
simplify61.6
story generation74.9
summarize65.7
Questions

Frequently asked questions

Can I run DeepSeek V4 Pro 0813 in the EU?

Yes. HostYourAI runs DeepSeek V4 Pro 0813 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 Pro 0813 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 Pro 0813 cost?

Via the shared EU router you pay €2.30 per million input tokens and €4.60 per million output tokens, with no fixed costs. For high volume or isolation you can also run DeepSeek V4 Pro 0813 on a dedicated GPU instance, billed per minute.

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

The platform

One platform, four layers

Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.

Code

Your coding agent on open models in Europe, set up with one command.

Open

Control

Keys, budgets and guardrails per team, and personal data stopped before any model sees it.

Open

Serve

Shared per token, or running for you alone, from European data centres.

Open

EU compute

Private GPUs in Europe, H100 to B300, sized for response time, generation speed and concurrent users.

Open

Try DeepSeek V4 Pro 0813 for free

Creating an account takes a minute. Test DeepSeek V4 Pro 0813 straight away in the playground.

  • Jantine
  • Hans
  • Sander
  • Jos
  • Daan
  • Kyra
  • Margriet
  • Stan
The team behind HostYourAI