Meta: Llama 4 Scout

by Meta

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 (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Avg Score

74.3%

258 answers

Avg Latency

2.8s

25 runs

Pricing

$0.08

input

$0.30

output

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.

Model	Cost
Meta: Llama 3.3 70B Instruct	-33%
Google: Gemini 2.0 Flash	-2%

Same Quality, Faster

Models with similar or better performance but lower latency.

Model	Latency
Google: Gemini 2.5 Flash Lite	-60%
Google: Gemini 2.0 Flash	-56%
Google: Gemini 2.5 Flash	-49%
Anthropic: Claude 3 Haiku	-41%
Google: Gemini 3 Flash Preview	-34%

Same Cost, Better

Models at a similar price point with higher benchmark scores.

Model	Score
Google: Gemini 2.0 Flash	+4%

Other Models from Meta

Compare performance with other models from the same creator

Model	Score	Latency	Cost/1M
Meta: Llama 4 Maverick	76.4%	2.6s	$0.38
Meta: Llama 3.3 70B Instruct	71.7%	3.5s	$0.21
Meta: Llama 3.2 3B Instruct	53.9%	3.0s	$0.02
Meta: Llama 3.2 1B Instruct	39.3%	4.4s	$0.11
Meta: Llama 3.1 405B (base)	3.2%	45.0s	$4.00
Meta: Llama Guard 4 12B	—	—	$0.18
Llama Guard 3 8B	—	—	$0.04
Meta: Llama 3.3 70B Instruct	—	—	$0.0000
Meta: Llama 3.2 3B Instruct	—	—	$0.0000
Meta: Llama 3.2 90B Vision Instruct	—	—	$0.38
Meta: Llama 3.2 11B Vision Instruct	—	—	$0.05
Meta: Llama 3.1 8B Instruct	—	—	$0.03
Meta: Llama 3.1 405B Instruct	—	—	$0.0000
Meta: Llama 3.1 405B Instruct	—	—	$3.50
Meta: Llama 3.1 70B Instruct	—	—	$0.40
Meta: LlamaGuard 2 8B	—	—	$0.20
Meta: Llama 3 70B Instruct	—	—	$0.35
Meta: Llama 3 8B Instruct	—	—	$0.04

Benchmark Performance

How this model performs across different benchmarks

Benchmark	Score	Rank
Math Bench: Addition (1-10)	100.0%	9 / 35
Math Bench: Subtraction (1-10)	100.0%	11 / 35
Math Bench: Multiplication (1-10)	100.0%	11 / 35
Math Bench: Division (1-10)	100.0%	1 / 35
Math Bench: Arithmetic (1-100)	100.0%	11 / 35
Customer service	100.0%	5 / 17
Structured Customer Support Extraction	100.0%	4 / 17
Repetitive Onomatopoeia Response Benchmark	100.0%	1 / 17
SaaS Customer Support Extraction and Strategy	100.0%	1 / 16
Math Bench: Arithmetic (1-1000)	93.5%	18 / 35
Venture Capital Terms Benchmark	91.4%	17 / 25
Motor production test	90.0%	28 / 35
KUKA force Torque control programming skills	80.0%	14 / 17
Spatial Reasoning: Germany	78.8%	29 / 35
Karlsruhe Local Knowledge Benchmark	74.2%	22 / 35
Product Recommendations	63.8%	25 / 36
Character Frequency Bench	61.8%	27 / 35
Customer support	60.0%	13 / 17
solve n-queens in clojure in one shot	20.0%	14 / 16
Current Global Political Leaders	20.0%	5 / 17
German Memelord Bench	5.9%	32 / 35
Money Boy Cultural Literacy Test	2.9%	26 / 35
Karl Lorey knowlege	1.6%	20 / 36

Price vs Performance

Compare cost efficiency across all models

Current model

Other models

X-axis uses log scale for better visualization of price range

Score Over Time

Performance trends across all benchmark runs

Benchmark Activity

Number of benchmark runs over time

Quickstart

Get started with this model using OpenRouter

View on 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