Back to Models

Llama 4 Maverick Instruct (17Bx128E)


                        meta-llama/llama-4-maverick-17b-128e-instruct-fp8

Meta Chat

Description

Llama 4 Maverick Instruct (17Bx128E) by Meta. This model supports chat capabilities. Variant: Instruct.

Specifications

Context Length:: 1048576
Variant:: Instruct
Quantization:: FP8
Parameters:: 17B

Pricing

Input Cost:: $0.0540/100K tokens
Output Cost:: $0.1700/100K tokens

Usage Example

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.yourproxy.com/v1",
  apiKey: process.env.PROXY_KEY,
});

const completion = await client.chat.completions.create({
  model: "meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
  messages: [{ role: "user", content: "Hello!" }],
});