AtlasAI Center AI tool intelligence
Search
Meta · API model

Llama 4 Scout

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...

Context
1.31M
Input / 1M
$0.1
Output / 1M
$0.3
Released
Apr 5, 2025
View on OpenRouterFind it in the catalog
Specifications

Llama 4 Scout specs

Provider
Meta
Type
API model
Model ID
meta-llama/llama-4-scout
Context window
1,310,720 tokens1.31M
Input price
$0.1per 1M input tokens
Output price
$0.3per 1M output tokens
Accepts
image, text
Produces
text
Released
Apr 5, 2025
Source
OpenRouter
Overview

About Llama 4 Scout

Llama 4 Scout is an API model from Meta, released on Apr 5, 2025, with a context window of 1,310,720 tokens, pricing of $0.1 per million input tokens and $0.3 per million output tokens. It accepts image, text input and produces text output.

At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0013.

Specs are sourced from OpenRouter and were last checked on Oct 24, 2026. Always confirm current pricing and limits with the provider before production use.

Tool callingStructured outputsJSON mode
FAQ

Llama 4 Scout questions

What is the context window of Llama 4 Scout?

Llama 4 Scout supports a context window of 1,310,720 tokens.

How much does Llama 4 Scout cost?

Llama 4 Scout is listed at $0.1 per million input tokens and $0.3 per million output tokens on OpenRouter.

When was Llama 4 Scout released?

Llama 4 Scout was published on Apr 5, 2025.

What inputs does Llama 4 Scout accept?

Llama 4 Scout accepts image, text input and produces text output.