DeepSeek R1 Distill Llama 70B

Description

DeepSeek-R1-Distill-Llama-70B is a 70B model distilled from DeepSeek-R1 using Llama-3.3-70B-Instruct as the base. Features chain-of-thought reasoning with <think> tokens, 128K context, and strong performance on AIME 2024, MATH-500, and LiveCodeBench. Optimized for complex math, coding, and reasoning tasks.

Providers

Capabilities

EU-Compliant API Access

Use DeepSeek R1 Distill Llama 70B with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

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-r1-distill-llama-70b",
    messages: [
      { role: "user", content: "Hello!" }
    ],
  }),
});

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