AI model · Meta
Llama 4 Maverick
Model ID: meta-llama/llama-4-maverick
- Input
- $0.19 per 1M tokens
- Output
- $0.65 per 1M tokens
- Context
- 1M tokens at once
- Max output
- 16K tokens per reply
- Released
- 5 Apr 2025 Meta
What it can do
- NoReasoning
- YesTool calling
- YesImage input
- YesOpen weights
- NoFree to use
Takes text, image; gives text.
How its listing describes it
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...
Sources
- Meta: Llama 4 Maverick on OpenRouter — read 2 Oct 2026