Llama 4 Scout
Rank #133
meta-llama
meta-llama/llama-4-scout-17b-16e-instruct
Usage data date 2026-07-26 · updated daily
Usage and specs
Daily rank#133
Daily tokens12.1B
Daily requests5.5M
Daily change
−6.3%
Context window10M
Released
What is Llama 4 Scout
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.
Llama 4 Scout capabilities
Input: Text、Image Output: Text
Llama 4 Scout API pricing
Input · per 1M tokens$0.10
Output · per 1M tokens$0.30
USD list-price snapshot, not independently verified; confirm current pricing and terms on the provider site before purchase.