# Llama 4 Scout: AI model fact sheet

- **Provider:** meta
- **Released:** 2025-04-05
- **Context window:** 10,000,000 tokens
- **Parameters:** 17B active (109B total)
- **API pricing:** $0.25 / 1M input, $0.50 / 1M output
- **OpenRouter ID:** meta-llama/llama-4-scout
- **Capabilities:** conversation, reasoning, code-generation, analysis

Llama 4 Scout is Meta's compact yet powerful multimodal model with 17B active parameters and 16 experts (109B total parameters). It fits on a single H100 GPU with Int4 quantization and offers an industry-leading 10M token context window, outperforming Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 across various benchmarks.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| Context Length | 10M tokens |
| LiveCodeBench | 32.8% |
| SWE-bench Verified | 54.6% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/llama-4-scout