Description
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.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Meta: Llama 4 Scout (meta-llama/llama-4-scout)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "meta-llama/llama-4-scout",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Meta: Llama 4 Scout model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
- Images
API Pricing
- Input: 0.08$ / 1M tokens
- Output: 0.3$ / 1M tokens
- Image: 0$ / image
Token Limits
- Max Output: 16,384 tokens
- Max Context: 327,680 tokens
Subscription Tiers
- free
- pro
- ultimate