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...
Rank
#166
Down 2% week over week
Tokens
16.8B
2026-10-24
Requests
6.9M
6,902,066
Tool calls
-
Input / M
$0.19
Output / M
$0.65
Cache / M
$0.05
Context
524K
524,288 tokens