Back to all models
meta-llama
meta-llamaMeta: 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...
meta-llama/llama-4-scout
Context Size
327.68K
Input Price
492 Ks/M
Output Price
1,845 Ks/M
Architecture
Text
Image
Supported Parameters
frequency_penaltymax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerLlama4
Max Completion16,384 tokens
Provider Context327.68K tokens
ModeratedNo