Llama 4 405B

meta/llama-4-405b

Try in Playground

Largest open-weight model with strong reasoning.

Context window

256Ktokens

Input price

$2.70/ 1M tokens

Output price

$2.70/ 1M tokens

P50 latency

680ms

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: "meta/llama-4-405b",
  messages: [{ role: "user", content: "Hello!" }],
});

Capabilities

textcode

Throughput: 55 tok/s · Released 2025-09