Llama 4 Scout

Meta · released 5 Apr 2025

Input$0.1per 1M tokens

Output$0.3per 1M tokens

Context1,311Ktokens

WeightsOpen

context on a 1K–2M scale

About

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...

Details

Lab: Metaopenrouter.ai · 3 Oct 2026
Context: 1,311Kopenrouter.ai · 3 Oct 2026
Input price: $0.1 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $0.3 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 16,384 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, imageopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list

Ling 3.1 Flash 262K Context Free plan Apodex 1.1 Mini (free) 262K Context Free plan Pareto 26.10 Preview 1,049K Context GPT-6.1 Sol 1,050K Context GPT-6.1 Sol Pro 1,050K Context Claude Sonnet 5.5 1,000K Context

Listed on Inferse

Newest Models in 2026466 listed
Longest-Context Models in 2026466 listed
Cheapest Language Models in 2026444 listed
Models with Tool Calling in 2026398 listed
Vision Language Models in 2026295 listed
Open-Weight Models in 2026178 listed
Meta Models: Pricing per 1M Tokens and Context (2026)14 listed

Sources

openrouter.ai/meta-llama/llama-4-scout· checked 3 Oct 2026