Nova Pro

Approved Data Classifications

Description

Amazon Nova is a suite of advanced foundation models developed by Amazon Web Services (AWS) to deliver high-performance, cost-effective solutions for various AI applications. These models are designed to cater to a wide range of tasks, including text understanding, image and video processing, and creative content generation.

Understanding Models:

• Amazon Nova Micro: A text-only model optimized for low-latency responses and cost efficiency, suitable for tasks like language understanding and code completion.

• Amazon Nova Lite: A multimodal model capable of processing text, image, and video inputs, offering fast performance at a low cost, ideal for interactive applications.

• Amazon Nova Pro: A highly capable multimodal model that balances accuracy, speed, and cost, excelling in complex tasks such as video summarization and software development.

Creative Content Generation Models:

• Amazon Nova Canvas: An image generation model that creates professional-grade images from text or image prompts, featuring tools for editing and customization.

• Amazon Nova Reel: A video generation model that produces high-quality videos from text and images, allowing control over visual style and camera motions through natural language prompts.

These models are integrated with Amazon Bedrock, enabling seamless deployment and scalability for developers aiming to build and enhance AI-driven applications.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
nova-pro	Not Disclosed	Image, Text, Video	Text	300,000	$0.80/1M input $3.20/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "nova-pro",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.chat.completions.create(
      model="nova-pro", # model to send to the proxy
      messages = [
          { role: "system", content: "You are a helpful assistant." },
          {
              "role": "user",
              "content": "Write a haiku about an Alligator."
          }
      ]
  )

  print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "nova-pro",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)