meta-llamaVision
Meta: 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...
Context
10M tokens
Input / 1M tokens
$0.10
Output / 1M tokens
$0.30
Benchmark
—
Pricing
Input tokens$0.10 per 1M tokens
Output tokens$0.30 per 1M tokens
Technical details
Model IDmeta-llama/llama-4-scout
Context window10M tokens
Input modalitiestext, image
Output modalitiestext
TokenizerLlama4
Max output tokens16,384
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'meta-llama/llama-4-scout',
messages: [{ role: 'user', content: 'Hello!' }],
})