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
1,048.576K
Input Price
28,125 pts/M1,730 Ks/M
Output Price
97,875 pts/M6,019 Ks/M
Architecture
Text
Image
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerLlama4
Max Completion16,384 tokens
Provider Context128K tokens
ModeratedNo
CreatedApr 5, 2025