Nova Pro (US) pricing, context window and limits
Nova Pro (US) costs $0.8 per million input tokens and $3.2 per million output tokens at Amazon Bedrock list price. It accepts up to 300,000 tokens of context and returns up to 10,000 tokens.
- Model id
bedrock/us.amazon.nova-pro-v1:0 - Snapshot
What does Nova Pro (US) cost?
| Input | $0.8 |
|---|---|
| Output | $3.2 |
| Cached input (read) | $0.2 |
| Cache write | $0.8 |
US dollars per million tokens. A dash means no price is published.
How much can Nova Pro (US) read and write?
| Context window | 300,000 |
|---|---|
| Max output | 10,000 |
What can Nova Pro (US) do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | No |
| Input | text, image, video, pdf |
| Output | text |
What does a request to Nova Pro (US) cost?
| A typical request: 1,000 tokens in, 500 out | $0.0024 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.011 |
| 1,000 typical requests | $2.4 |
| 1 million tokens in and 1 million out | $4 |
Input read from the provider's prompt cache costs $0.2 per million tokens instead of $0.8, 75% less. A request that repeats a 1,000-token prompt from the cache costs $0.0018 instead of $0.0024.
Among 199 Amazon Bedrock models with a published price, Nova Pro (US) is the 82nd cheapest by input price. Its context window is the 108th largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Nova Pro (US) through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/us.amazon.nova-pro-v1:0. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- Nova Premier (US)$2.5 in · $12.5 out · 1M context
- Nova Micro (US)$0.035 in · $0.14 out · 128K context
- Nova Lite (US)$0.06 in · $0.24 out · 300K context
- Nova 2 Lite (US)$0.33 in · $2.75 out · 1M context
- Nova 2 Lite (JP)$0.396 in · $3.311 out · 1M context
- Nova 2 Lite (Global)$0.3 in · $2.5 out · 1M context
- Nova Pro (EU)$0.92 in · $3.68 out · 300K context
- Nova Micro (EU)$0.04 in · $0.16 out · 128K context
- Nova Lite (EU)$0.069 in · $0.276 out · 300K context
- Nova 2 Lite (EU)$0.374 in · $3.157 out · 1M context
- Nova Lite (CA)$0.064 in · $0.256 out · 300K context
- Nova Pro (APAC)$0.84 in · $3.36 out · 300K context
Which models from other providers are similar to Nova Pro (US)?
These are the closest in context window and input price, one per provider.
- Qwen3-Coder 480B-A35B InstructAlibaba Qwen · $0.861 in · $3.441 out · 262K context
- Kimi K2.6Moonshot AI · $0.95 in · $4 out · 262K context
- GPT-5.4 miniOpenAI · $0.75 in · $4.5 out · 400K context
- Grok Build 0.1xAI Grok · $1 in · $2 out · 256K context
- GLM-5Zhipu GLM · $1 in · $3.2 out · 205K context