Nova Pro API Pricing
As of October 10, 2026, Nova Pro costs $0.80 per 1M input tokens and $3.20 per 1M output tokens from Amazon Bedrock, the lowest of 2 providers, with cache reads at $0.20 per 1M tokens. It has a 300,000-token context window and returns up to 10,000 tokens per response.
- Input
- $0.80 / 1M tokens
- Output
- $3.20 / 1M tokens
- Cache read
- $0.20 / 1M tokens
- Context window
- 300,000 tokens
- Max output
- 10,000 tokens
- Providers
- 2
- Added to LiteLLM
- December 2024
Nova Pro pricing by provider
7 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Amazon Bedrock | amazon.nova-pro-v1:0 | $0.80 | $3.20 | $0.20 | 300K |
| Vercel AI Gateway | vercel_ai_gateway/amazon/nova-pro | $0.80 | $3.20 | – | 300K |
| Amazon BedrockAPAC cross-region | apac.amazon.nova-pro-v1:0 | $0.84 | $3.36 | $0.21 | 300K |
| Amazon Bedrockus-gov-east-1 | bedrock/us-gov-east-1/amazon.nova-pro-v1:0 | $0.96 | $3.84 | $0.24 | 300K |
| Amazon Bedrockus-gov-west-1 | bedrock/us-gov-west-1/amazon.nova-pro-v1:0 | $0.96 | $3.84 | $0.24 | 300K |
| Amazon BedrockEU cross-region | eu.amazon.nova-pro-v1:0 | $1.05 | $4.20 | $0.2625 | 300K |
| Amazon BedrockUS cross-region | us.amazon.nova-pro-v1:0 | $0.80 | $3.20 | $0.20 | 300K |
Other Nova Pro prices on Amazon Bedrock
| Flex input | $0.40 per 1M tokens |
| Flex output | $1.60 per 1M tokens |
What Nova Pro costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Amazon Bedrock | $3.20 |
| Vercel AI Gateway | $3.20 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Amazon Bedrock | $8.64 |
| Vercel AI Gateway | $8.64 |
Nova Pro features
- Function calling
- Structured output
- Image input
- PDF input
- Prompt caching
Use Nova Pro with LiteLLM
Call Nova Pro through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="amazon.nova-pro-v1:0",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: nova-pro
litellm_params:
model: amazon.nova-pro-v1:0
aws_region_name: os.environ/AWS_REGION_NAMEcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "nova-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'Nova Pro FAQ
How much does Nova Pro cost?
Nova Pro costs $0.80 per 1M input tokens and $3.20 per 1M output tokens from Amazon Bedrock, the lowest of 2 providers, with cache reads at $0.20 per 1M tokens.
What is the context window of Nova Pro?
Nova Pro has a 300,000-token context window and returns up to 10,000 tokens per response.
Which providers offer Nova Pro?
Nova Pro is available from 2 providers through LiteLLM: Amazon Bedrock and Vercel AI Gateway.
How do I call Nova Pro with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="amazon.nova-pro-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 Pro support?
Nova Pro supports function calling, structured output, image input, PDF input and prompt caching.
When did LiteLLM add Nova Pro?
Nova Pro was added to LiteLLM's model price file in December 2024.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: Amazon Bedrock, Vercel AI Gateway.
Provider pages: Amazon Bedrock, Vercel AI Gateway.
