All Models

Llama 4 Scout

llama Tool Calling Attachments Open Weights Structured Output

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...

Providers 3
Released Apr 5, 2025
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

10.3
Intelligence Index
8.2
Coding Index
14
Math Index

Available Providers (3)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NanoGPT meta-llama/llama-4-scout $0.09/MTok $0.46/MTok 328K 65.5K
OpenRouter meta-llama/llama-4-scout $0.10/MTok $0.30/MTok 1.3M 16.4K
Kilo Gateway meta-llama/llama-4-scout $0.10/MTok $0.30/MTok 327.7K 16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output