← All models
M

Meta: Llama 4 Scout

meta-llama/llama-4-scout

VisionTool useJSONStreaming

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...

Pricing

Input

$0.08 / 1M

Output

$0.3 / 1M

Specs

Context

10,000,000 tokens

Input

text, image

Output

text

Knowledge cutoff: 2024-08-31

Released: 2025-04

Supported parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

420,123 downloads/mo
1,297 likes
other
View on HuggingFace →