Llama 4 Scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

by Meta

Overview

Quick stats across all benchmark runs.

Score

38%

277 benchmarks

Avg Latency

6.6s

757 requests

Pricing

$0.08 in / $0.30 out

per 1M tokens

Context

328K

tokens

Alternatives

Models with similar or better quality but different tradeoffs

Same Quality, Cheaper

Models with similar or better performance at a lower cost per token.

No alternatives found

Same Quality, Faster

Models with similar or better performance but lower latency.

Model	Latency
Claude 3 Haiku	-46%
Nova 2 Lite	-24%
Gemini 2.0 Flash	-24%
Gemini 3 Flash Preview	-17%
Llama 4 Maverick	-12%

Same Cost, Better

Models at a similar price point with higher benchmark scores.

Model	Score
Ministral 3 8B 2512	+0%

Benchmark Performance

How this model performs across different benchmarks

Benchmark	Score	Rank
Venture Capital Terms Benchmark	91%	5 / 21
Spatial Reasoning: Germany	79%	24 / 29
Categorization Bench	76%	5 / 54
Niederstetten Benchmark	62%	12 / 35
Character Frequency Bench	62%	22 / 29
Explain Like I'm 5	57%	18 / 47
Money Boy Cultural Literacy Test	38%	70 / 107
German Memelord Bench	10%	27 / 29

Price vs Performance

Compare cost efficiency across all models

Current model (baseline)

Other models (relative score)

Y-axis shows score difference from shared benchmarks. X-axis uses log scale.

Score Over Time

Performance trends across all benchmark runs

Benchmark Activity

Number of benchmark runs over time

Quickstart

View on OpenRouter

Get started with this model using OpenRouter

import { OpenRouter } from "@openrouter/sdk";

const openrouter = new OpenRouter({
  apiKey: "<OPENROUTER_API_KEY>"
});

const completion = await openrouter.chat.completions.create({
  model: "meta-llama/llama-4-scout",
  messages: [
    {
      role: "user",
      content: "Hello!"
    }
  ]
});

console.log(completion.choices[0].message.content);

Get your API key at openrouter.ai/keys

Other Models from Meta

Compare performance with other models from the same creator

Model	Latency	Cost/1M	Score
Llama 3.2 1B Instruct	30.8s	$0.11	42%
Llama 3.3 70B Instruct	20.5s	$0.21	41%
Llama 4 Maverick	4.7s	$0.38	38%
Llama 3.2 3B Instruct	31.0s	$0.19	0%
Llama Guard 3 8B	6.6s	$0.26	—
Llama 3.1 70B Instruct	14.5s	$0.40	—
Llama 3.2 90B Vision Instruct	—	$0.38	—
Llama Guard 4 12B	513ms	$0.18	—
Llama 3.1 8B Instruct	23.7s	$0.03	—
Llama 3 70B Instruct	20.1s	$0.63	—
Llama 3 8B Instruct	8.8s	$0.04	—
Llama 3.2 11B Vision Instruct	44.8s	$0.24	—
Llama 3.1 405B Instruct	—	Free	—
Llama 3.1 405B (base)	39.5s	$4.00	—
LlamaGuard 2 8B	1.6s	$0.20	—