Maverick
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 pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.
Performance Tier
Maverick is a flagship model from Llama 4 : the most capable in their lineup.
Best-in-class model from this provider. Highest performance across benchmarks, ideal for demanding tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.150 |
| Output (completion) | $0.600 |
Capabilities
Benchmarks
Recommended Use Cases
Strengths
- Most capable open-weight model from Meta
- Strong general reasoning and coding (HumanEval 89.5%)
- Native multimodal support (text + image)
- Open-weight with commercially permissive license
Limitations
- Lags behind top proprietary models on science reasoning (GPQA 69.8%)
- Large model — requires significant compute for self-hosting
Resources
This model may use your data for training
