Meta: Llama 4 Scout

Meta: Llama 4 Scout is a large language model from Meta Llama. It costs $0.100 per million input tokens and $0.300 per million output tokens. Its context window is 1.3M tokens.

Tool callingStructured outputOpen weightsimage input

Input / 1M tokens: $0.100
Output / 1M tokens: $0.300
Cached input / 1M: -
Context window: 1.3M

Who serves it cheapest

3 hosts serve Llama 4 Scout. Same weights, same API - the price difference is pure margin and routing.

Providers serving Meta: Llama 4 Scout, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
DeepInfraCheapestfp8	$0.100	$0.300	328K	-	99.9%
Novitabf16	$0.180	$0.590	131K	-	99.9%
Google	$0.250	$0.700	1.3M	-	-

The spread between DeepInfra and Google is 2.4× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index: 6.5
Coding index: 8.2
Agentic index: 0.5

About 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...

Specifications

Meta: Llama 4 Scout specifications
Model ID	`meta-llama/llama-4-scout`
Provider	Meta Llama
Context window	1.3M tokens
Max output	16K tokens
Input modalities	text, image
Output modalities	text
Knowledge cutoff	2024-08-31
Open weights	Yes - meta-llama/Llama-4-Scout-17B-16E-Instruct
Released	April 5, 2025

Cheaper alternatives

Models that cost less than Llama 4 Scout while keeping at least half its context window and every input modality it supports.

Muse Spark 1.3 Contributor

$0.100 in · $0.200 out

1.2× cheaper

Muse Spark 1.2 Contributor

$0.100 in · $0.200 out

1.2× cheaper

Qwen3.5-Flash

$0.065 in · $0.260 out

1.3× cheaper

Qwen3.7 Flash

$0.030 in · $0.130 out

2.7× cheaper

Lyria 3 Pro Preview

Free in · Free out

Frequently asked

How much does Meta: Llama 4 Scout cost?

$0.100 per million input tokens and $0.300 per million output tokens.

What is the context window of Meta: Llama 4 Scout?

1.3M tokens, with up to 16K tokens of output per request.

Which provider serves Meta: Llama 4 Scout cheapest?

DeepInfra at $0.100 per million input tokens - 2.4× cheaper than Google, the most expensive of the 3 hosts serving it.