meta-llamaBerbayar
Meta: Llama 4 Scout
meta-llama/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...
Harga input / 1M token
$0.1000
Harga output / 1M token
$0.3000
Context length
1.310.720
Modalitas
- Input
- text, image
- Output
- text
Parameter yang didukung
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Rilis
5 April 2025