Meta: Llama 4 Maverick

meta-llama/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...

Modalities
TextImage
In / out price
₩351 / ₩1,221
1M
Context
1.05M
Released
Apr 6, 2025

Providers

Several places host the same model. Requests are spread by priority and health, and a local GPU always goes first when one is available.

ProviderContextQuantizationMax outputPriorityState
OpenRouter1.05M50unknown