Amazon Nova Premier
Amazon's most capable Nova multimodal model for complex reasoning and as a teacher model for distillation, with first-party AWS Bedrock on-demand rates and a 1M-token context window.
Source: Amazon Nova pricing, Amazon Bedrock pricing, Amazon Nova overview
Specs
Details that do not fit the rate card above.
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate | Batch |
|---|---|---|
| Input | $2.5 / M | $1.25 / M |
| Output | $12.5 / M | $6.25 / M |
| Cache read | $0.625 / M | n/a |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Provider
Where this model runs, and what it charges.
| Platform | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|
AWS Bedrock | $2.5 | $12.5 | $0.625 | ✓ | Direct |
Price history
Has this model gotten cheaper or more expensive?
More from Amazon
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Amazon Nova Premier call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.