MetaSees images
Llama 4 Maverick
meta-llama/llama-4-maverickLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Context
524K tokens
Input, 1M tokens
$0.4
Output, 1M tokens
$1.15
Benchmark
—
Uptime and speed
Loading…
Pricing
Charged from your prepaid balance for the tokens actually used.
Input tokens$0.4 per 1M tokens
Output tokens$1.15 per 1M tokens
Cache read$0.2 per 1M tokens
Apps and activity
Loading…
Technical details
Model IDmeta-llama/llama-4-maverick
Context window524K tokens
AcceptsText, Images
ProducesText
TokenizerLlama4
Max output tokens32,768
How to connect
The API is OpenAI-compatible: the official SDKs, LangChain and any client with a "base URL" field work.
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-maverick',
messages: [{ role: 'user', content: 'Hello!' }],
})Start using Llama 4 Maverick
Create a free account, get a key in your dashboard and send your first request. Top up your balance when you need it.