Meta: Llama 4 Maverick

By Meta Llama

Released: 2025-04-05

Visit Website

API

LLM

RAG

Meta Llama

Paid

New

Meta Llama Llama 4 Maverick, developed by Meta, features 17B parameters, MoE architecture and 1,049k-token context window. 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. optimised for vision-language tasks, Maverick is instruction-tuned for assistant-like behaviour, 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. Available at $0.15/1M tokens.

Specifications

AI Evaluation