Llama 4 Scout
AffordableRun locallyMeta's efficient multimodal MoE model with 16 experts.
17B active parameters with native multimodal input and 10M-token context window. Fast inference with strong text and vision capabilities.
▼
Llama 4 Scout is somewhat expensive at $0.10/M tokens input and $0.30/M tokens output. The model supports vision/image input, a 328K context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Run locally
Run Llama 4 Scout on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.
ollama pull llama4:16x17b
Misc
Compare with
Frequently Asked Questions about Llama 4 Scout▼
When was Llama 4 Scout released?
▼
Llama 4 Scout was released on April 5, 2025.
Who created Llama 4 Scout?
▼
Llama 4 Scout was created by Meta.
How much does Llama 4 Scout cost?
▼
Llama 4 Scout costs $0.10/M input tokens and $0.30/M output tokens.
What is Llama 4 Scout API pricing?
▼
The Llama 4 Scout API is priced at $0.10 per million input tokens and $0.30 per million output tokens. You can access Llama 4 Scout through idapt.app alongside 200+ other AI models in one workspace.
Is Llama 4 Scout a reasoning model?
▼
No, Llama 4 Scout is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Llama 4 Scout support image or vision input?
▼
Yes, Llama 4 Scout supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does Llama 4 Scout support audio?
▼
No, Llama 4 Scout does not support audio input.
What is the context window of Llama 4 Scout?
▼
Llama 4 Scout has a context window of 328K tokens, meaning it can process approximately 245,760 words of context at once.
Is Llama 4 Scout open source?
▼
Llama 4 Scout is a proprietary model developed by Meta. The model weights and training data are not publicly available.
What is Llama 4 Scout good at?
▼
Based on benchmark data, Llama 4 Scout excels at: visual analysis and image understanding. It is Meta's capable model suitable for a wide range of tasks.
Where can I use Llama 4 Scout?
▼
You can chat with Llama 4 Scout on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Llama 4 Scout through Meta's own API or platform.