Llama 4 Scout
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...
The figures
- Made by
- Meta
- Model ID
- meta-llama/llama-4-scout
- Input
- $0.1 per million tokens
- Output
- $0.3 per million tokens
- Context window
- 1.31M tokens
- Longest answer
- 16K tokens
- Takes in
- text, image
- Gives back
- text
- Reasoning
- No
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 5 Apr 2025
Read on 3 Oct 2026.