DeepSeek V3

by deepseek

Chat

Description

DeepSeek V3 is a 671B parameter Mixture-of-Experts (MoE) model with 37B activated parameters per token. It uses Multi-head Latent Attention (MLA) for efficient KV caching and supports a 128K context window. Strong performance on code and math benchmarks.

Providers

Nebius

View provider details and policies.

Pricing

Input$0.50 /1M tokens

Output$1.50 /1M tokens

Get Started

Specifications

Context128K tokens

Parameters—

License—

Released—

Capabilities

ToolsJSON ModeStreaming

EU-Compliant API Access

Use DeepSeek V3 with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

JavaScript

const response = await fetch("https://api.eurouter.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${process.env.EUROUTER_API_KEY}`,
  },
  body: JSON.stringify({
    model: "deepseek-v3",
    messages: [
      { role: "user", content: "Hello!" }
    ],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

More from deepseek

DeepSeek R1 Distill Llama 70B

$0.90 / $0.90

DeepSeek R1

$0.80 / $2.40

Explore more

Nebius provider

View Nebius's data policy and model catalog.

Browse all models

Explore the full EUrouter model catalog.

Models API

List models and capabilities via the API.

Quickstart

Authenticate and make your first request.

Integrate AI without GDPR risk.

You need AI that won't create compliance headaches. Your data stays in the EU, GDPR is enforced by default, and every request is routed for the best balance of cost, latency, and uptime — reducing risk while improving performance.

Get Started

GDPR by default

EU data residency

Smart routing