Llama 4 Scout
Efficient open model with an industry-leading 10M-token native context.
Llama 4 Scout 17B Instruct (16E) activates 17B of 109B parameters and supports native multimodal input with a 10M-token native context window.
- Provider
- Meta
- Type
- Language model
- Released
- Apr 5, 2025
- Context window
- 10M tokens
- Max output
- 16K tokens
- Price
- $0.10 input / $0.30 output per 1M tokens
- Input
- text, image
- Output
- text
- Open weights
- Yes
- License
- Llama 4 Community License
Best for
- Long context
- Local & on-device
- High volume / low cost
Strengths
- 10M-token native context
- Cheap to serve
More from Meta
- Llama 4 Maverick — Meta. Meta’s 128-expert open multimodal MoE model.
- Muse Spark 1.3 — Meta. Meta’s multimodal reasoning model for long-running agents and coding.
- Muse Image — Meta. Meta’s low-cost image model.
- V-JEPA 2 — Meta. Meta’s open JEPA world model for video understanding, prediction and robot planning.
- Llama Guard 4 12B — Meta. Open multimodal safety classifier for prompts and responses.