Nova 2 Lite

Approved Data Classifications

Description

Amazon Nova 2 Lite is AWS's fast, cost-efficient multimodal model for high-volume workloads. It accepts text, images, video, and documents as input and produces text output, supports up to a 1M token context window, and can generate up to 65,536 tokens per response. Nova 2 Lite is designed for tasks like RAG, agentic workflows, and multimodal understanding where low latency and cost efficiency are priorities. Pricing is based on input and output tokens; see Amazon Bedrock pricing for current rates.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
nova-2-lite	Not Disclosed	Document, Image, Text, Video	Text	1,000,000	See Amazon Bedrock pricing

info

• 1M represents 1 Million Tokens
• Pricing varies by region and usage tier; see Amazon Bedrock pricing for current rates

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-2-lite",
    "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-2-lite", # 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-2-lite",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)

---

References

1. AWS - AI Service Card (Amazon Nova 2 Lite)
   https://aws.amazon.com/nova/service-card/
2. AWS - What is Amazon Nova 2?
   https://docs.aws.amazon.com/nova2/latest/userguide/what-is-nova2.html
3. AWS - Amazon Bedrock supported foundation models
   https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html
4. AWS - Amazon Bedrock pricing
   https://aws.amazon.com/bedrock/pricing/