# Nova Lite 2 API Pricing

As of November 7, 2026, Nova Lite 2 costs $0.38 per 1M input tokens and $3.16 per 1M output tokens on EmpirioLabs AI, with cache reads at $0.2128 per 1M tokens. It has a 1,000,000-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/nova-lite-2
- Lab: Amazon
- LiteLLM model name: `empiriolabs/nova-lite-2`
- Context window: 1,000,000 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: November 4, 2026
- Prices updated: November 6, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| EmpirioLabs AI | `empiriolabs/nova-lite-2` | $0.38 | $3.16 | $0.2128 | – | – | 1M |

## Cost examples

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

- EmpirioLabs AI: $2.34

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

- EmpirioLabs AI: $4.432

## Features

Supported: Function calling, Image input, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="empiriolabs/nova-lite-2",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## Cost calculator

10,000 requests a day with 1,000 input and 500 output tokens each, at EmpirioLabs AI's price: $0.00196 per request, $19.60 per day, $588 per month (30 days). Try other numbers at https://models.litellm.ai/calculator?model=nova-lite-2

## FAQ

### How much does Nova Lite 2 cost?

Nova Lite 2 costs $0.38 per 1M input tokens and $3.16 per 1M output tokens on EmpirioLabs AI, with cache reads at $0.2128 per 1M tokens.

### What is the context window of Nova Lite 2?

Nova Lite 2 has a 1,000,000-token context window and returns up to 131,072 tokens per response.

### Which providers offer Nova Lite 2?

Nova Lite 2 is available from EmpirioLabs AI through LiteLLM, using the model name empiriolabs/nova-lite-2.

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

Use the LiteLLM Python SDK with model="empiriolabs/nova-lite-2", 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 Lite 2 support?

Nova Lite 2 supports function calling, image input, reasoning and prompt caching.

### When did LiteLLM add Nova Lite 2?

Nova Lite 2 was added to LiteLLM's model price file on November 4, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change.