meta-llamaBerbayar
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Harga input / 1M token
$0.2000
Harga output / 1M token
$0.6960
Context length
1.048.576
Modalitas
- Input
- text, image
- Output
- text
Parameter yang didukung
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rilis
5 April 2025