# Nova 2 Multimodal Embeddings API Pricing

As of October 10, 2026, Nova 2 Multimodal Embeddings costs $0.135 per 1M input tokens on Amazon Bedrock. It has an 8,172-token context window.

- Page: https://models.litellm.ai/models/nova-2-multimodal-embeddings
- Lab: Amazon
- LiteLLM model name: `amazon.nova-2-multimodal-embeddings-v1:0`
- Context window: 8,172 tokens
- Added to LiteLLM: January 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 | `amazon.nova-2-multimodal-embeddings-v1:0` | $0.135 | $0 | – | – | – | 8K |
| Amazon Bedrock (us-gov-west-1) | `bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0` | $0.162 | $0 | – | – | – | 8K |

## Cost examples

Embedding 10,000 documents of 500 tokens each:

- Amazon Bedrock: $0.675

## Features

Supported: Audio input, Video input.

## Use it with LiteLLM

```python
from litellm import embedding

response = embedding(
    model="amazon.nova-2-multimodal-embeddings-v1:0",
    input=["hello world"],
)
```

## FAQ

### How much does Nova 2 Multimodal Embeddings cost?

Nova 2 Multimodal Embeddings costs $0.135 per 1M input tokens on Amazon Bedrock.

### What is the context window of Nova 2 Multimodal Embeddings?

Nova 2 Multimodal Embeddings has an 8,172-token context window.

### Which providers offer Nova 2 Multimodal Embeddings?

Nova 2 Multimodal Embeddings is available from Amazon Bedrock through LiteLLM, using the model name amazon.nova-2-multimodal-embeddings-v1:0.

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

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

### What features does Nova 2 Multimodal Embeddings support?

Nova 2 Multimodal Embeddings supports audio input and video input.

### When did LiteLLM add Nova 2 Multimodal Embeddings?

Nova 2 Multimodal Embeddings was added to LiteLLM's model price file in January 2026.

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