Llama 4 Scouton Krater.ai
The efficient member of Meta's Llama 4 family, Scout offers impressive capability with a massive 10M token context window at lower cost than Maverick.
Released April 5, 2025
Specifications
Llama 4 Scout at a glance
Context
1.3M tokens
Max output
16.4K tokens
Input
Text, Image
Output
Text
Input price
$0.10 / 1M
Output price
$0.30 / 1M
Knowledge cutoff
2024-08-31
Capabilities
What it is good at
Catalog capabilities
- Accepts image input
- Generates text responses
- Supports tool calling
- Supports structured outputs
- Massive 10M token context window
- Cost-effective Llama 4 performance
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
8.2
Agentic index score
1.1
Intelligence index score
10.3
Design Arena dataviz rank
#109
Design Arena uicomponent rank
#111
Compare
Compare Llama 4 Scout
Llama 4 Scout vs Llama 4 Maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward
Open comparisonLlama 4 Scout vs Llama Guard 4 12B
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification.
Open comparisonLlama 4 Scout vs Llama 3.1 70B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
Open comparisonFAQ
Questions about Llama 4 Scout
Clear answers based on the model catalog and Krater access.
Use Llama 4 Scout in your API
Connect with Krater's unified API.