Meta: Llama 4 Scout

Llama4

Multimodal

Paid

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...

Parameters

Context Window

327,680

tokens

Input Price

$0.08

per 1M tokens

Output Price

$0.3

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Good reasoning with solid logical foundations

Math

Coding

Capable of generating functional code with good practices

Knowledge

Modalities

Input Modalities

text,image

Output Modalities

text

LLM Price Calculator

Calculate the cost of using this model

Input Tokens (0.00000008/token)$0.000120

Output Tokens (0.00000030/token)$0.000900

Common Scenarios:

Input Cost:$0.000120

Output Cost:$0.000900

Total Cost:$0.001020

Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage

$0.0038

~10 requests

Moderate Usage

$0.0380

~100 requests

Heavy Usage

$0.3800

~1000 requests

Enterprise

$3.8000

~10,000 requests

Note: Estimates based on current token count settings per request.

Last Updated: 2026/04/11