Llama 4 Scout
Meta馃嚭馃嚫
meta-llama/llama-4-scoutLlama 4 Scout is Meta's efficient open-weight Mixture-of-Experts model with an industry-leading long context window, designed for tasks requiring extensive context handling alongside multimodal understanding. It offers a lighter, faster alternative to Llama 4 Maverick.
Cost rate
0.1x
Context
1.3M
Released
Apr 5, 2025
Input
TextImage
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Image understanding
#119 路 top 75%
Legal & Government
#237 路 top 61%
Mathematical
#242 路 top 62%
Entertainment, Sports, & Media
#243 路 top 59%
Performance
Median latency and throughput measured across recent requests.
Throughput68 tok/s
Latency