Llama 4 70B Instruct

meta/llama-4-70b

Try in Playground

Open-source workhorse with great price/performance.

Context window

128Ktokens

Input price

$0.55/ 1M tokens

Output price

$0.65/ 1M tokens

P50 latency

240ms

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-4-70b",
  messages: [{ role: "user", content: "Hello!" }],
});

Capabilities

textcode

Throughput: 130 tok/s · Released 2025-08