Meta: Llama 4 Scout
Meta's Llama 4 Scout offers a generous 327K context window, multimodal support, and tool/function calling at a competitive price, making it a capable option for document-heavy workflows; benchmark scores are modest but the combination of long context and open-ecosystem accessibility gives it practical business appeal.
Assessment date: April 4, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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..
Capabilities
Architecture
| Modality | Text + Image → Text |
| Tokenizer | Llama4 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Meta: Llama 4 Scout stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
meta-llama/llama-4-scout
|
| Provider | meta-llama |
| Model Family | Llama 4 |
| Release Date | April 5, 2025 |
| Context Length | 327,680 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.08 | $0.000080 |
| Output | $0.30 | $0.000300 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
