Amazon Bedrock Pricing
Amazon Bedrock charges between $0.140 and $12.50 per 1 million output tokens, depending on the model. Amazon Nova Nova Micro is the cheapest at $0.140/1M output and $0.035/1M input; Amazon Nova Nova Premier is the most expensive at $12.50/1M output. The largest context window is 1.0M tokens (Amazon Nova Nova Premier). Prices are USD, current as of July 20, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.035/1M
Amazon Nova Nova Micro
Cheapest output
$0.140/1M
Amazon Nova Nova Micro
Longest context
1.0M
Amazon Nova Nova Premier
Models priced
8
Avg $4.02/1M output
Pricing by model
All prices in USD per 1 million tokens. All 8 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Amazon Nova Nova Micro | $0.035 | $0.140 | 128K |
| Nova Micro 1.0 | $0.035 | $0.140 | 128K |
| Amazon Nova Nova Lite | $0.060 | $0.240 | 300K |
| Nova Lite 1.0 | $0.060 | $0.240 | 300K |
| Amazon Nova Nova Pro | $0.800 | $3.20 | 300K |
| Nova Pro 1.0 | $0.800 | $3.20 | 300K |
| Amazon Nova Nova Premier | $2.50 | $12.50 | 1.0M |
| Nova Premier 1.0 | $2.50 | $12.50 | 1.0M |
Frequently asked questions
How much does Amazon Bedrock cost per 1M tokens?
Amazon Bedrock pricing ranges from $0.140 to $12.50 per 1 million output tokens across 8 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.
What is the cheapest Amazon Bedrock model?
Amazon Nova Nova Micro is the cheapest Amazon Bedrock model on both axes — $0.035 per 1M input tokens and $0.140 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.
What is the largest Amazon Bedrock context window?
Amazon Nova Nova Premier has the largest context window in the Amazon Bedrock catalog at 1.0M input tokens, with up to 10K output tokens per response.
How do I calculate my actual Amazon Bedrock bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator