# Llama 4 Scout

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 (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.

Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

## Model Information

- **Organization**: [Meta](/llm.txt)
- **Slug**: llama-4-scout
- **Available at Providers**: 17
- **Release Date**: April 5, 2025

### Benchmark Scores
- GPQA: 0.572

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | llama-4-scout | 0.20 | 0.20 |  | [View](https://aihubmix.com/model/llama-4-scout) |
| [Helicone](/llm/helicone.txt) | Meta Llama 4 Scout 17B 16E | 0.08 | 0.30 |  | [View](https://www.helicone.ai/model/llama-4-scout) |
| [Mammouth AI](/llm/mammouth.txt) | llama-4-scout | 0.15 | 0.60 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | Llama 4 Scout |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | Llama 4 Scout | 0.08 | 0.30 |  | [View](https://openrouter.ai/meta-llama/llama-4-scout-17b-16e-instruct) |
| [ValorGPT](/llm/valorgpt.txt) | Llama 4 Scout |  |  |  | [View](https://www.valorgpt.com/models/meta-llama-llama-4-scout) |
| [Vercel AI Gateway](/llm/vercel.txt) | Llama 4 Scout 17B 16E Instruct | 0.17 | 0.66 |  |  |
| [Yupp](/llm/yupp.txt) | Llama 4 Scout (OpenRouter) |  |  |  |  |
| [Routeway](/llm/routeway.txt) | Meta: Llama 4 Scout | 0.10 | 0.23 |  | [View](https://routeway.ai/models) |
| [LangDB](/llm/langdb.txt) | llama-4-scout |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | Meta: Llama 4 Scout | 0.08 | 0.30 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | Meta: Llama 4 Scout | 0.08 | 0.30 |  |  |
| [Okara](/llm/okara.txt) | Llama 4 Scout |  |  |  | [View](https://okara.ai/ai-models/llama-4-scout) |
| [CometAPI](/llm/cometapi.txt) | Llama-4-Scout | 0.22 | 1.15 |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | llama-4-scout | 0.09 | 0.33 |  |  |
| [Airforce API](/llm/airforce.txt) | llama-4-scout |  |  |  |  |
| [Writingmate](/llm/writingmate.txt) | Meta: Llama 4 Scout |  |  |  | [View](https://writingmate.ai/models/meta-llama/llama-4-scout) |

---

[← Back to all providers](/llm.txt)