Meta/llama-4-scout-17b-16e-instruct/Released Apr 2025

Llama 4 Scout

MoE multimodal model, long context

Fine-tunableCommercial use
Text

About Llama 4 Scout

Llama 4 Scout Instruct is a 109B-parameter Multimodal LLM designed for advanced text and image understanding across multiple languages.

It excels in multi-document analysis, codebase reasoning, and complex multimodal tasks that require processing both text and images, especially where long context windows and multilingual capabilities are valuable.

Some other noteworthy use cases of Llama 4 Scout Instruct include multi-document summarization for legal or financial analysis, and highly personalized task automation using years of user data.

MetricValue
Parameter Count109 billion
Mixture of ExpertsYes
Active Parameter Count17 billion
Context Length327,680 tokens
MultilingualYes
Quantized*No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Ready to build with Llama 4 Scout?

Try Llama 4 Scout in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "llama-4-scout-17b-16e-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'

API endpoint

See the API reference for request and response formats.

POSThttps://hub.oxen.ai/api/ai/chat/completions