AI model · Meta
Llama 4 Scout
Model ID: meta-llama/llama-4-scout
- Input
- $0.10 per 1M tokens
- Output
- $0.30 per 1M tokens
- Context
- 1.3M 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 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Sources
- Meta: Llama 4 Scout on OpenRouter — read 2 Oct 2026