Llama 4 Scout 17B 16E Instruct

JSON →
meta multimodal
textimage

A 17-billion-parameter mixture-of-experts instruction-tuned model from Meta with 16 experts, designed for efficient and scalable text and image understanding.

context window 131K tokens
max output 8K tokens
input price $0.11 / 1M tokens
output price $0.34 / 1M tokens
streamingcode-generationfunction-callingtool-usejson-modevision
releasedApr 2025
knowledge cutoffDec 2024