Back to all models
meta-llama

Meta: 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...

meta-llama/llama-4-maverick

Context Size

524.288K

Input Price

52,500 pts/M3,229 Ks/M

Output Price

150,000 pts/M9,225 Ks/M


Architecture

Text
Image

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Details

TokenizerLlama4
Max Completion32,768 tokens
Provider Context524.288K tokens
ModeratedNo
CreatedApr 5, 2025