DeepSeek

DeepSeek V4

deepseek/deepseek-v4

Try in Playground

MoE frontier model excelling at coding and math.

Context window

128Ktokens

Input price

$0.14/ 1M tokens

Output price

$0.28/ 1M tokens

P50 latency

290ms

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-v4",
  messages: [{ role: "user", content: "Hello!" }],
});

Capabilities

textcode

Throughput: 110 tok/s · Released 2026-02