← model directory

meta-llama

Meta: Llama 4 Scout

meta-llama/llama-4-scout

↓ runs free on your own hardware

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...

specs & pricing
Type
text
Provider
meta-llama
Model ID
meta-llama/llama-4-scout
Capabilities
vision, tools
Context window
10M tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.088 / 1M tokens
Output price
$0.33 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.