← all models

Llama 4 Scout

meta

openrouter
Parameters 17B openrouter api · from the Hugging Face repo
Context 1.25M 1310720 tokens
Input $0.10 OpenRouter
Output $0.30 OpenRouter
Cache read — OpenRouter

Accepts

text image

Capabilities

frequency_penalty logit_bias max_tokens min_p presence_penalty repetition_penalty response_format seed stop structured_outputs temperature tool_choice tools top_k top_p

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter meta-llama/llama-4-scout huggingface meta-llama/Llama-4-Scout-17B-16E-Instruct version slug meta-llama/llama-4-scout-17b-16e-instruct name Meta: Llama 4 Scout display name Llama 4 Scout

Identifiers

Vendor
meta
OpenRouter
meta-llama/llama-4-scout
Hugging Face
meta-llama/Llama-4-Scout-17B-16E-Instruct
Version slug
meta-llama/llama-4-scout-17b-16e-instruct
Released
2025-04-05T19:31:59.000Z
First seen
59 d ago
Last crawled
19 min ago