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.
Scout est un modèle équilibré de Llama 4 : un bon compromis entre bonnes performances à un prix raisonnable.
Bon rapport coût-performance. Fiable pour la plupart des usages professionnels sans tarification premium.
| Type | par 1M tokens |
|---|---|
| Entrée (prompt) | $0.080 |
| Sortie (complétion) | $0.300 |
Ce modèle peut utiliser vos données pour l'entraînement