Back to catalog
MetaHosted on Luminet

Llama 4 Scout

meta/llama-4-scout

Try in Playground

17B active / 109B total. 10M context window. Single-GPU friendly with INT4.

Context window
10Mtokens
Input price
$0.18/ 1M tokens
Output price
$0.59/ 1M tokens
P50 latency
95ms

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

Capabilities

textvision

Throughput: 460 tok/s · Released 2025-04