Llama 4 Scout

About 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 Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Meta Model Lineup

Compare all models from Meta to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

MiMo-V2-Flash (free)

Other

Input: $0.09

Output: $0.29

Context: 262k

Gemini 2.0 Flash Lite

Google

Input: $0.07

Output: $0.30

Context: 1.0M

GPT-4o-mini (batch)

OpenAI

Input: $0.07

Output: $0.30

Context: 128k

Seed 1.6 Flash

Bytedance Seed

Input: $0.07

Output: $0.30

Context: 262k

💡 Cheaper Alternatives

Same Brand (Meta)

Cross Brand

🚀 Quick Start

Get started with Llama 4 Scout API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="meta-llama/llama-4-scout-17b-16e-instruct",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision