# Nova 2 Pro Preview API Pricing

As of October 10, 2026, Nova 2 Pro Preview costs $1.25 per 1M input tokens and $10.00 per 1M output tokens on Amazon Bedrock, with cache reads at $0.3125 per 1M tokens. It has a 1,000,000-token context window and returns up to 64,000 tokens per response.

- Page: https://models.litellm.ai/models/nova-2-pro-preview
- Lab: Amazon
- LiteLLM model name: `amazon.nova-2-pro-preview-20251202-v1:0`
- Context window: 1,000,000 tokens
- Max output: 64,000 tokens
- Added to LiteLLM: February 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Amazon Bedrock (snapshot 20251202) | `amazon.nova-2-pro-preview-20251202-v1:0` | $1.25 | $10.00 | $0.3125 | – | – | 1M |
| Amazon Bedrock (APAC cross-region, snapshot 20251202) | `apac.amazon.nova-2-pro-preview-20251202-v1:0` | $1.375 | $11.00 | $0.3438 | – | – | 1M |
| Amazon Bedrock (EU cross-region, snapshot 20251202) | `eu.amazon.nova-2-pro-preview-20251202-v1:0` | $1.375 | $11.00 | $0.3438 | – | – | 1M |
| Amazon Bedrock (US cross-region, snapshot 20251202) | `us.amazon.nova-2-pro-preview-20251202-v1:0` | $1.375 | $11.00 | $0.3438 | – | – | 1M |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Amazon Bedrock: $7.50

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Amazon Bedrock: $14.50

## Features

Supported: Function calling, Structured output, Image input, PDF input, Video input, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="amazon.nova-2-pro-preview-20251202-v1:0",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Nova 2 Pro Preview cost?

Nova 2 Pro Preview costs $1.25 per 1M input tokens and $10.00 per 1M output tokens on Amazon Bedrock, with cache reads at $0.3125 per 1M tokens.

### What is the context window of Nova 2 Pro Preview?

Nova 2 Pro Preview has a 1,000,000-token context window and returns up to 64,000 tokens per response.

### Which providers offer Nova 2 Pro Preview?

Nova 2 Pro Preview is available from Amazon Bedrock through LiteLLM, using the model name amazon.nova-2-pro-preview-20251202-v1:0.

### How do I call Nova 2 Pro Preview with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="amazon.nova-2-pro-preview-20251202-v1:0", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Nova 2 Pro Preview support?

Nova 2 Pro Preview supports function calling, structured output, image input, PDF input, video input, reasoning and prompt caching.

### When did LiteLLM add Nova 2 Pro Preview?

Nova 2 Pro Preview was added to LiteLLM's model price file in February 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json