DevTk.AI

Amazon Nova Premier

Amazon

Amazon Nova Premier by Amazon: $2.50/M cache-miss input, $12.50/M output tokens. Cached input: $0.625/M. 1.0M context, 10K max output. Vision & Video. Price verified 2026-11-18.

Input Price

$2.50

cache miss / 1M tokens

Cached Input

$0.625

per 1M tokens

Output Price

$12.50

per 1M tokens

Context Window

1.0M

tokens

Amazon Nova Premier price history

No price changes recorded for Amazon Nova Premier in our AI API price change log (earliest entry: 2026-05-27). Current rates last verified against the official Amazon pricing page on 2026-11-18. See all AI API price changes

Specifications

ProviderAmazon
Model IDamazon.nova-premier-v1:0
Input Price$2.50 / 1M cache-miss tokens
Cached Input Price$0.625 / 1M tokens
Output Price$12.50 / 1M tokens
Context Window1.0M tokens
Max Output10K tokens
Capabilities
textvisionvideofunction_calling
Release Date2025-04-30
Pricing SourceOfficial Amazon pricing
Price Verified2026-11-18
NotesMost capable Amazon Nova 1 model and a teacher model for distillation, via Amazon Bedrock (us-east-1 on-demand; cross-region profile us.amazon.nova-premier-v1:0). Batch is 50% off ($1.25/$6.25).

Monthly Cost Estimates

Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.

Daily TokensMonthly CostAnnual Cost
10K $2.25 $27.00
50K $11.25 $135.00
100K $22.50 $270.00
500K $112.50 $1350.00
1.0M $225.00 $2700.00

How Amazon Nova Premier Pricing Compares

Standard cache-miss input / output prices per 1M tokens, compared with active, price-verified models priced in USD. Cached, batch and long-context rates are not included.

  • Within Amazon: 4 of 4 other active Amazon models have a lower input price, and 4 have a lower output price.
  • Similar context window: among the 67 active models with a 500K–2.0M token context window, Amazon Nova Premier ranks #49 from cheapest at a 50/50 input/output mix. Cheapest: Qwen3.7 Flash ($0.03/$0.13). Most expensive: GPT-5.5 Pro ($30.00/$180.00).

Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Amazon Nova Premier Key Details

  • Pricing: $2.50/M cache-miss input tokens, $0.625/M cached input tokens, $12.50/M output tokens
  • Context window: 1.0M tokens — 28 of 90 active models we track have a larger window
  • Max output: 10K tokens per response
  • Capabilities: text, vision, video, function_calling
  • Highlights: Most capable Amazon Nova 1 model and a teacher model for distillation, via Amazon Bedrock (us-east-1 on-demand; cross-region profile us.amazon.nova-premier-v1:0). Batch is 50% off ($1.25/$6.25).
  • Released: 2025-04-30

Other Amazon Models

Similar Price Range

Related Tools

FAQ

How much does Amazon Nova Premier cost?

Amazon Nova Premier costs $2.50 per million cache-miss input tokens and $12.50 per million output tokens. Cached input costs $0.625 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $26.25/month before cache-hit savings.

What is Amazon Nova Premier's context window?

Amazon Nova Premier supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. The maximum output per response is 10K tokens.

Is Amazon Nova Premier good for my use case?

Amazon Nova Premier supports text, vision, video, function_calling. We track pricing and limits, not output quality, so test it on your own prompts before committing. The price comparison above lists cheaper and pricier models with a similar context window, and the Pricing Calculator estimates your monthly cost across all of them.