Meta: Llama 4 Maverick
6.9 / 10
1M context
Proprietary
About this model
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...
Benchmark Scores
MATH
61.2
MBPP
77.6
Technical Specs
- Architecture: text+image->text
- Context Window: 1,048,576 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.2 / 1M tokens | 0.696 / 1M tokens | USD |