Llama 4 Scout is a general-purpose, natively multimodal model with 17 billion active parameters (and 109 billion total) designed for personalized experiences. It has a 10m token context window
The company that provides the model
The number of tokens you can send in a prompt
The maximum number of tokens a model can generate in one request
The cost of prompt tokens sent to the model
The cost of output tokens generated by the model
When the model's knowledge ends
When the model was launched
Capability for the model to use external tools
Ability to process and analyze visual inputs, like images
Support for multiple languages
Whether the model supports fine-tuning on custom datasets
The pricing for Llama 4 Scout is not yet available.
Llama 4 Scout supports a context window of up to 10,000,000 tokens.
Llama 4 Scout can generate up to 8,192 tokens in a single output.
Llama 4 Scout was released on April 5, 2025.
The knowledge cut-off date for Llama 4 Scout is not available.
Yes, Llama 4 Scout supports vision capabilities.
Yes, Llama 4 Scout supports tool calling or functions.
Yes, Llama 4 Scout supports multiple languages.
No, Llama 4 Scout does not support fine-tuning.
You can find the official documentation for Llama 4 Scout here.
Collaborate with thousands of AI builders to discover, manage, and improve prompts—free to get started.
