NVIDIA NIM: Llama 4 Maverick 17B 128E

stable

Llama 4 Maverick 17B 128E is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

meta__llama-4-maverick-17b-128e-instructllamareleased Apr 1, 2025

Provider Quick start

Context

128K

tokens

Max output

4.1K

tokens

Input

per 1M

Output

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

NVIDIA NIM

128K--

Pricing

Item	Price	Unit
Input	-	per 1M tokens
Output	-	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: meta__llama-4-maverick-17b-128e-instruct
Family: llama
Status: stable
Knowledge: -
Released: Apr 1, 2025

Gateway Config

API: 2024-01-01
Auth: NVIDIA_API_KEY
Discovery: static
Provider type: meta

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@nvidia-nim/meta__llama-4-maverick-17b-128e-instruct",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://integrate.api.nvidia.com/v1

Chat completions

https://integrate.api.nvidia.com/v1/chat/completions

Model

meta__llama-4-maverick-17b-128e-instruct

Auth env

NVIDIA_API_KEY

Llama 4 Maverick 17B 128E FAQ

What is the context window of Llama 4 Maverick 17B 128E?

Llama 4 Maverick 17B 128E accepts up to 128K tokens of context and returns up to 4.1K output tokens on NVIDIA NIM.

What can Llama 4 Maverick 17B 128E do?

Llama 4 Maverick 17B 128E supports chat, function calling and image input. It accepts text and image input.

How do I call Llama 4 Maverick 17B 128E through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @nvidia-nim/meta__llama-4-maverick-17b-128e-instruct. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.