Scout
Llama 4Balanced
Tool UseVisionStructured Output
About this model
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...
Performance Tier
Balanced
Scout is a balanced model from Llama 4 : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.080 |
| Output (completion) | $0.300 |
Capabilities
Context Length328K
Max Output Tokens16K
TokenizerLlama4
Inputtext, image
Outputtext
Release DateApril 5, 2025
Benchmarks
General Intelligence
MMLU
83.5%
Mathematics
MATH-500
78.5%
Programming
HumanEval
84%
Reasoning
IFEval
85.2%
Recommended Use Cases
General ChatCodingSummarizationTranslation
Strengths
- Massive 10M token context window — largest in the industry
- Efficient MoE architecture (17B active / 109B total)
- Strong instruction following (IFEval 85.2%)
- Open-weight with commercially permissive license
Limitations
- Less capable than Maverick on complex reasoning
- Quality may degrade at extreme context lengths
Resources
This model may use your data for training
