Back to all models
meta-llama
meta-llamaMeta: 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
30,000 pts/M
Output Price
120,000 pts/M
Architecture
Text
Image
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerLlama4
Max Completion16,384 tokens
Provider Context1,048.576K tokens
ModeratedNo
CreatedApr 5, 2025