Llama 4 Scout 17B

Meta

A compact multimodal model using mixture-of-experts architecture for text and image understanding. Designed for efficient multimodal experiences with vision support.

Try Now

Capabilities

Tool Use

Image Input

PDF Input

Example Use Cases

Efficient multimodal tasks

Vision-enabled workflows

Compact llama 4

Technical Specifications

Context Window

131,072 tokens

Max Output

8,192 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.08

Non-Reasoning Output

$0.30

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Poor tool calling capabilities and hallucinates web searches

Recommended Replacement

MiniMax M2.7