# Nova 2 Lite

Nova 2 Lite adds a larger context window, optional extended thinking, web grounding, and code execution on top of the first-generation Nova models. You still get multimodal inputs with pricing aimed at everyday production traffic.

- **Model ID:** `amazon/nova-2-lite`
- **Type:** chat
- **Providers:** bedrock
- **Context window:** 1,000,000
- **Maximum output tokens:** 1,000,000
- **Pricing:** $0.33/1M input tokens, $2.75/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/nova-2-lite

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'amazon/nova-2-lite',
  prompt: 'Why is the sky blue?'
})
```

## About

Nova 2 Lite is the cost-focused model in Amazon's second-generation Nova family. The context window moves from 300K tokens on first-gen Nova Lite and Nova Pro up to 1M tokens. Extended thinking lets the model run deliberate multi-step reasoning before it answers. You set it to low, medium, or high. It stays off by default when you don't need it.

Amazon pairs Nova 2 Lite and Nova 2 Pro with built-in web grounding and code execution: the model can pull current public information and run code so answers stay tied to fresh data, not only to training cutoffs.

Inputs include text, images, video, and documents (including PDFs) within the window of 1M tokens. That covers long documents with images, video with transcripts, and similar mixed workloads that first-generation Nova models handle with tighter limits.

## What to consider

When extended thinking is on, reasoning tokens are billed at the output token rate. If you use medium or high thinking budgets often, monitor output token spend in the AI Gateway cost dashboard.

## When to use

### Best For

- Mixed-format document processing that combines PDFs, images, and text in a single long-context request
- Workflows that need current information via web grounding (with citations when the provider returns them)
- Agentic task orchestration where the model calls external tools across multiple steps
- Analytical tasks where you toggle extended thinking selectively, using fast extraction by default and deeper reasoning when needed
- Video and image analysis combined with document comprehension in a unified context of 1M tokens

### Consider Alternatives When

- The workload is text-only and cost is the main concern. Nova Micro remains cheaper and faster for pure text
- You need multimodal inputs but not reasoning. First-generation Nova Lite handles simpler vision tasks at lower cost
- The task demands the highest accuracy on structured documents and you don't need second-gen reasoning features. Evaluate Nova Pro

## Best for

- **Mixed-format document processing:** Combine PDFs, images, and text in a single long-context request
- **Current information workflows:** Web grounding provides up-to-date information with citations when the provider returns them
- **Agentic task orchestration:** The model calls external tools across multiple steps
- **Selective extended thinking:** Toggle deeper reasoning on analytical tasks and use fast extraction by default
- **Unified video and document analysis:** Video and image analysis combined with document comprehension in a single context of 1M tokens

## Consider alternatives

- **Text-only cost-focused workloads:** Nova Micro remains cheaper and faster for pure text processing
- **Simple multimodal tasks:** First-generation Nova Lite handles simpler vision tasks at lower cost without reasoning overhead
- **Highest structured-document accuracy:** Evaluate Nova Pro when second-gen reasoning features aren't required

## Frequently asked questions

### How do I control extended thinking?

Under `providerOptions.bedrock.reasoningConfig`, set `maxReasoningEffort` to `low`, `medium`, or `high`. Extended thinking is off by default, so you avoid reasoning-token charges until you enable it.

### What does web grounding do?

The model can search the public web during a request and ground answers in what it finds, with citations when the provider returns them. Use it when answers need current facts, not only the training snapshot.

### How large is the context window compared to first-gen Nova models?

1M tokens. That's more than three times the 300K-token context in Nova Lite and Nova Pro, and nearly eight times Nova Micro's 128K.

### Can Nova 2 Lite run code during a conversation?

Yes. Amazon documents code execution for Nova 2 models so the model can run code as part of the response flow. Use it for calculations, data transforms, and similar tasks the provider supports.

### How are reasoning tokens billed?

Reasoning tokens are billed at the output token rate. With thinking disabled (the default), you pay only standard input and output costs.

### Is Nova 2 Lite a direct replacement for first-gen Nova Lite?

No, it's a successor but not a drop-in replacement. Nova 2 Lite has different pricing and a different capability profile. For simple multimodal tasks where first-gen Nova Lite performs well, upgrading may not cut costs. The value lies in the reasoning, grounding, and code execution features the original lacked.

## Links

- [Model page](https://vercel.com/ai-gateway/models/nova-2-lite)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://www.aboutamazon.com/news/aws/aws-agentic-ai-amazon-bedrock-nova-models)
- [Provider pricing](https://aws.amazon.com/bedrock/pricing/)