Model Overview
Meta · Active Model
- Long-Context
- API Available
- Production Ready
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...
- Developer
- Meta
- Release Date
- April 5, 2025
- Context Window
- 1,048,576 tokens≈ 1,398 words
- API Access
- Publicly AvailableIntegrate via official API
- Input Cost
- $0.15per million tokens
- Output Cost
- $0.60per million tokens