Back to all LLMs

Meta
Llama 4 Scout
Overview
Llama 4 Scout is Meta’s compact yet powerful large language model, designed for high-performance tasks such as long-context reasoning, multi-document summarization, and code analysis. It employs a Mixture-of-Experts (MoE) architecture, activating 17 billion parameters per token from a pool of 16 experts, totaling 109 billion parameters. This design allows for efficient inference while maintaining high accuracy.
Model Information
Max Input
10M
Tokens
Input Price
$0.15
per 1M Tokens
Output price
$0.50
per 1M Tokens
Size
109B
Billion Parameters
Release date
2025-04-05
Licence
Llama 4 Community License
Parameters
109B
Input Context Length
10M
Tokens
Output Context Length
-
Tokens
Features & Capabilities
Web Access
Yes
Real-time access to current web information
Multimodal
Yes
Ability to process multiple data types (text, images, etc...)
API
Sample code and API for GPT-4o Search Preview