G
GetLLMs

Llama 4 Maverick Instruct

Llama 4 Maverick Instruct is a powerful 17-billion parameter language model designed for conversational AI and instruction-based tasks.

Platform: Replicate
Text GenerationInstruction FollowingMixture of Experts
390.9k runs
Priced by multiple properties
License Check Required

🚀Function Overview

A large language model with mixture-of-experts architecture for generating text responses to prompts.

Key Features

  • 17 billion parameters with 128 experts
  • Configurable text generation controls (temperature, top_p, penalties)
  • Multimodal input capabilities
  • Iterator-style concatenated output

Use Cases

  • Conversational AI assistants
  • Content creation
  • Instruction-based task completion
  • Text generation with fine-tuned parameters

⚙️Input Parameters

prompt

string

Prompt

max_tokens

integer

The maximum number of tokens the model should generate as output

temperature

number

The value used to modulate the next token probabilities

presence_penalty

number

Presence penalty

frequency_penalty

number

Frequency penalty

top_p

number

Top-p (nucleus) sampling

💡Usage Examples

Example 1

Input Parameters

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

Output Results

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