Cracked AI Engineering

Llama-4-Scout-17B-16E-Instruct-FP8 vs Llama-4-Maverick-17B-128E-Instruct-FP8

Compare Llama-4-Scout-17B-16E-Instruct-FP8 by Llama and Llama-4-Maverick-17B-128E-Instruct-FP8 by Llama. See detailed specifications, pricing, and capabilities side-by-side.

Quick Overview

Llama-4-Scout-17B-16E-Instruct-FP8

Llama

128K tokens context • Free

View full specifications →

Llama-4-Maverick-17B-128E-Instruct-FP8

Llama

128K tokens context • Free

View full specifications →

Detailed Comparison

Specification
Llama-4-Scout-17B-16E-Instruct-FP8
Llama-4-Maverick-17B-128E-Instruct-FP8
Provider
Llama
Llama
Context Window
128K tokens
128K tokens
Max Output Tokens
4K tokens
4K tokens
Input Pricing (per 1M tokens)
Free
Free
Output Pricing (per 1M tokens)
Free
Free
Release Date
Apr 2025
Apr 2025

Capabilities

Capability
Llama-4-Scout-17B-16E-Instruct-FP8
Llama-4-Maverick-17B-128E-Instruct-FP8
Text Generation
Vision
Function Calling
File Attachments

Which Model Should You Choose?

Choose Llama-4-Scout-17B-16E-Instruct-FP8 if:

    Choose Llama-4-Maverick-17B-128E-Instruct-FP8 if: