← All models View on HuggingFace →
M
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
VisionTool useJSONStreaming
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...
Pricing
Input
$0.15 / 1M
Output
$0.6 / 1M
Specs
Context
1,048,576 tokens
Input
text, image
Output
text
Knowledge cutoff: 2024-08-31
Released: 2025-04
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
35,668 downloads/mo
489 likes
other image-text-to-text