Nova Premier API Pricing
- Input / output
- $2.50 / $12.50 per 1M tokens
- Cache read
- $0.625 / 1M
- Context
- 1M tokens
- Max output
- 10K tokens
As of October 21, 2026, Nova Premier costs $2.50 per 1M input tokens and $12.50 per 1M output tokens on Amazon Bedrock, with cache reads at $0.625 per 1M tokens. It has a 1,000,000-token context window and returns up to 10,000 tokens per response.
Nova Premier pricing by provider
1 listing across 1 provider. 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 | Batch in | Batch out | Context |
|---|---|---|---|---|---|---|---|
| Amazon Bedrock | amazon.nova-premier-v1:0 | $2.50 | $12.50 | $0.625 | $1.25 | $6.25 | 1M |
Other Nova Premier prices on Amazon Bedrock
| Priority input | $4.375 per 1M tokens |
| Priority output | $21.88 per 1M tokens |
What Nova Premier costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Amazon Bedrock | $11.25 |
| Amazon Bedrock batch | $5.625 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Amazon Bedrock | $27.50 |
Nova Premier cost calculator
At Amazon Bedrock's price ($2.50 input, $12.50 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $87.50 a day, about $2,625 a month. Change the numbers for your workload, or compare it with other models.
- Per request
- $0.00875
- Per day
- $87.50
- Per month (30 days)
- $2,625
Nova Premier features
- Function calling
- Structured output
- Image input
- PDF input
- Prompt caching
Use Nova Premier with LiteLLM
Call Nova Premier 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-premier-v1:0",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: nova-premier
litellm_params:
model: amazon.nova-premier-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 $LITELLM_API_KEY" \
-d '{
"model": "nova-premier",
"messages": [{"role": "user", "content": "Hello!"}]
}'Nova Premier FAQ
How much does Nova Premier cost?
Nova Premier costs $2.50 per 1M input tokens and $12.50 per 1M output tokens on Amazon Bedrock, with cache reads at $0.625 per 1M tokens. Batch requests cost $1.25 per 1M input tokens and $6.25 per 1M output tokens.
What is the context window of Nova Premier?
Nova Premier has a 1,000,000-token context window and returns up to 10,000 tokens per response.
Which providers offer Nova Premier?
Nova Premier is available from Amazon Bedrock through LiteLLM, using the model name amazon.nova-premier-v1:0.
How do I call Nova Premier with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="amazon.nova-premier-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 Premier support?
Nova Premier supports function calling, structured output, image input, PDF input and prompt caching.
When did LiteLLM add Nova Premier?
Nova Premier was added to LiteLLM's model price file in May 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: Amazon Bedrock.
Provider pages: Amazon Bedrock.