Description

Meta's LLaMA 4 Maverick is a versatile, natively multimodal model designed for creative and technical text generation. It offers best-in-class performance-to-cost ratio, with superior intelligence in text and visuals, and supports a massive 10 million token context window. Efficient enough to run on a single H100 GPU, it analyzes text, images, and video data, supports multiple languages, and enables new use cases around memory and long-context understanding, all while maintaining low costs and high efficiency.

Example API Call

curl -X POST https://neuralhubapi.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer NEURALHUB_API_KEY" \
-d '{
  "model": "meta/llama4-maverick-17b",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "What is the answer to life, the universe, and everything?" }
  ],
  "temperature": 0.7,
  "max_tokens": 500,
  "top_p": 0.9
}'

Response Format

The API returns an OpenAI-compatible response. Example:

{
  "id": "chatcmpl-<uuid>",
  "object": "chat.completion",
  "created": 1756503318,
  "model": "meta/llama4-maverick-17b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The answer to life, the universe, and everything is famously **42**, according to Douglas Adams' *The Hitchhiker’s Guide to the Galaxy*..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 26,
    "completion_tokens": 169,
    "total_tokens": 195
  }
}