DeepSeekHosted on Luminet

DeepSeek R2

deepseek/deepseek-r2

Try in Playground

Reasoning-tuned successor to R1.5. Verifier-aligned chain-of-thought, faster decode via optimised draft.

Context window

256Ktokens

Input price

$0.50/ 1M tokens

Output price

$2.00/ 1M tokens

P50 latency

220ms

Quick start

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.luminet.ai/v1",
  apiKey: process.env.LUMINET_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek/deepseek-r2",
  messages: [{ role: "user", content: "Hello!" }],
});

Capabilities

textcode

Throughput: 215 tok/s · Released 2026-05