meta/llama-4-maverick-instruct – Run with an API on Replicate

Official

meta / llama-4-maverick-instruct

A 17 billion parameter model with 128 experts

Warm

Public
379.8K runs
Priced by multiple properties
Weights
License

Iterate in playground

Run with an API

Playground API Examples README

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=meta/llama-4-maverick-instruct

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run meta/llama-4-maverick-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_p: 1,
  prompt: "Hello, Llama!",
  max_tokens: 1024,
  temperature: 0.6,
  presence_penalty: 0,
  frequency_penalty: 0
};

for await (const event of replicate.stream("meta/llama-4-maverick-instruct", { input })) {
  process.stdout.write(event.toString());
};

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run meta/llama-4-maverick-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The meta/llama-4-maverick-instruct model can stream output as it's running.
for event in replicate.stream(
    "meta/llama-4-maverick-instruct",
    input={
        "top_p": 1,
        "prompt": "Hello, Llama!",
        "max_tokens": 1024,
        "temperature": 0.6,
        "presence_penalty": 0,
        "frequency_penalty": 0
    },
):
    print(str(event), end="")

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run meta/llama-4-maverick-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "top_p": 1,
      "prompt": "Hello, Llama!",
      "max_tokens": 1024,
      "temperature": 0.6,
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/models/meta/llama-4-maverick-instruct/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?

Generated in

0.6 seconds

Input tokens

Output tokens

Tokens per second

40.50 tokens / second

Time to first token

8 milliseconds

Tweak it Report

Pricing

Model pricing for meta/llama-4-maverick-instruct. Looking for volume pricing? Get in touch.

$0.95

per million output tokens

or around 1,052,631 tokens for $1

$0.25

per million input tokens

or around 4,000,000 tokens for $1

Official models are always on, maintained, and have predictable pricing. Learn more.

Check out our docs for more information about how pricing works on Replicate.

Readme

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

These Llama 4 models mark the beginning of a new era for the Llama ecosystem. We are launching two efficient models in the Llama 4 series, Llama 4 Scout, a 17 billion parameter model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts.