Managed Inference and Agents API with Nova 2 Lite

Table of Contents [expand]

Last updated December 17, 2025

Nova 2 Lite is a large language model (LLM) from Amazon that supports conversational chat, tool-calling, and advanced reasoning capabilities with extended context. It offers built-in tools for web grounding and code interpretation, and is a fast and cost-effective solution you can use to power your AI applications.

  • Model ID: nova-2-lite
  • Region: us, eu

When to Use This Model

Nova 2 Lite supports a variety of common use cases, including process automation, code generation, and business intelligence. It’s optimized for high-volume apps that require speed and cost efficiency.

Usage

Nova 2 Lite follows our Claude /v1/chat/completions API schema.

To provision access to the model, attach nova-2-lite to your app $APP_NAME:

heroku ai:models:create -a $APP_NAME nova-2-lite

Using config variables, you can invoke nova-2-lite in a variety of ways:

Rate Limits

  • Maximum requests per minute: 150
  • Maximum tokens per minute: 800,000

Prompt Caching

Prompt caching isn’t supported for Nova 2 Lite.

Example curl Request

Get started quickly with an example request:

export INFERENCE_MODEL_ID=$(heroku config:get -a $APP_NAME INFERENCE_MODEL_ID)
export INFERENCE_KEY=$(heroku config:get -a $APP_NAME INFERENCE_KEY)
export INFERENCE_URL=$(heroku config:get -a $APP_NAME INFERENCE_URL)

curl $INFERENCE_URL/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_KEY" \
-d @- <<EOF
{
  "model": "$INFERENCE_MODEL_ID",
  "messages": [
    { "role": "user", "content": "Hello!" },
    { "role": "assistant", "content": "Hi there! How can I assist you today?" },
    { "role": "user", "content": "What's the weather like in Portland, Oregon right now?" }
  ],
  "temperature": 0.5,
  "max_tokens": 100,
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Fetches the current weather for a given city.",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "The name of the city to get weather for."
            }
          },
          "required": ["city"]
        }
      }
    }
  ],
  "tool_choice": "auto",
  "top_p": 0.9
}
EOF