Home › Providers › meta-llama › Meta: Llama 4 Scout

Meta: Llama 4 Scout API Pricing

Meta: Llama 4 Scout is an API model from meta-llama. It costs $0.1 per 1M input tokens and $0.3 per 1M output tokens. Its context window is 1,310,720 tokens with up to 16,384 output tokens. A workload of 10M input + 2M output tokens costs about $1.6 per month.
Input
$0.1
per 1M tokens
Output
$0.3
per 1M tokens
Cached input
—
per 1M tokens
Context window
1.31072M
1,310,720 tokens
Blended (80/20)
$0.14
per 1M tokens

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...

How much does Meta: Llama 4 Scout cost for a real workload?

At 10M input + 2M output tokens per month, Meta: Llama 4 Scout costs about $1.6 ($1 input + $0.6 output). Try your own volumes in the cost calculator.

What are cheaper alternatives to Meta: Llama 4 Scout?

Where to run Meta: Llama 4 Scout

AI/ML API: one API key for 400+ models, including most models tracked here · Novita AI: pay-as-you-go APIs for open models (DeepSeek, Qwen, Llama and more) plus GPU cloud. Prices there follow each platform's own catalog and can differ from the list prices tracked here.

Run it on AI/ML API →Run it on Novita AI →

Disclosure: links to these platforms may be affiliate links — if you sign up or buy through them, LLMPrices may earn a commission at no extra cost to you.

Compare Meta: Llama 4 Scout with other models

Meta: Llama 4 Scout vs Meta: Llama 3.1 8B InstructMeta: Llama 4 Scout vs Meta: Llama 3.2 1B InstructMeta: Llama 4 Scout vs Meta: Llama Guard 4 12BMeta: Llama 4 Scout vs Meta: Llama 3.2 3B InstructMeta: Llama 4 Scout vs Meta: Llama 3.3 70B InstructMeta: Llama 4 Scout vs Meta: Llama 3.1 70B Instruct

Frequently asked questions

How much does Meta: Llama 4 Scout cost?

Meta: Llama 4 Scout costs $0.1 per 1M input tokens and $0.3 per 1M output tokens (list price, snapshot October 22, 2026). At 10M input + 2M output tokens per month that is about $1.6.

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

Meta: Llama 4 Scout has a context window of 1,310,720 tokens and can return up to 16,384 output tokens per response.

What are cheaper alternatives to Meta: Llama 4 Scout?

Cheaper models include Qwen: Qwen3 30B A3B Instruct 2507 ($0.09 in / $0.3 out), Meta: Llama 3.2 3B Instruct ($0.0509 in / $0.335 out), Mistral: Mistral Small 4 (batch) ($0.075 in / $0.3 out). See the full list on this page.

Is Meta: Llama 4 Scout free to use?

No. Meta: Llama 4 Scout is a paid model at $0.1 input / $0.3 output per 1M tokens. 21 free models are listed on the free models page.

Provider: meta-llama · Model ID: meta-llama/llama-4-scout · Modality: text+image->text · Price snapshot October 22, 2026, refreshed daily. How we collect prices