Llama 4 Scout: API price, context window and how to connect

Llama 4 Scout by Meta: $0.1 per million input tokens, $0.3 per million output tokens, a 1.31M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

Updated Copy as Markdown
In this article

In short#

Meta's mixture-of-experts model: 17 of 109 billion parameters active, with native image understanding. A 1.3-million-token context window and open weights.

Specifications#

Provider Meta
Released 2025-04-05
Context window 1.31M tokens
Accepts text, images
Answers with text
Reasoning mode no
Tool calling yes
Open weights yes
Knowledge up to 2024-08
Identifier meta-llama/llama-4-scout

Price#

Per 1M tokens In dollars
Input (question, context) $0.1
Output (answer) $0.3

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.006. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

What it is good for#

  • Very long context cheaply
  • Running on your own hardware
  • Images as input

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
Llama 3.3 70B Instruct $0.1 $0.32 131K about the same
DeepSeek V4 Flash 0423 $0.091 $0.182 1.05M 1.4× cheaper
GPT-6 Luna $0.1 $0.5 1.05M 1.4× more expensive
GPT-6 Luna Pro $0.1 $0.5 1.05M 1.4× more expensive
Claude Haiku 5.5 $0.1 $0.5 1M 1.4× more expensive

Other Meta models#

How to connect in SKILLOK#

Llama 4 Scout works through OpenRouter: add an OpenRouter key in Settings → AI and pick the meta-llama/llama-4-scout model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.

Where the data comes from#

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

Was this helpful?