Provider
Amazon API pricing: every model compared
Amazon offers 5 models through its API in our data, priced from $0.035 to $2.50 per million input tokens. The newest is Nova 2 Lite, first listed on 2025-12-02.
- Models
- 5
- Cheapest input
- $0.035
- Priciest input
- $2.50
- Largest context
- 1,000,000
- With caching
- 1 of 5
- Open weights
- none
Cheapest
Nova Micro 1.0Amazon$0.035 in · $0.14 outLargest context
Nova 2 LiteAmazon1,000,000 tokensNewest
Nova 2 LiteAmazon2025-12-02Line-up
Every Amazon model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nova 2 Lite | $0.30 | $2.50 | 1,000,000 | 2025-12-02 |
| Nova Premier 1.0 | $2.50 | $12.50 | 1,000,000 | 2025-10-31 |
| Nova Lite 1.0 | $0.06 | $0.24 | 300,000 | 2024-12-05 |
| Nova Micro 1.0 | $0.035 | $0.14 | 128,000 | 2024-12-05 |
| Nova Pro 1.0 | $0.80 | $3.20 | 300,000 | 2024-12-05 |
Prices in US dollars per 1M tokens, newest first. Release dates are when our source first listed the model.
Overview
Amazon’s pricing at a glance
The spread between Amazon’s cheapest and most expensive model is large: Nova Premier 1.0 costs 71× more per input token than Nova Micro 1.0. Picking the smallest model that does the job well is usually the biggest saving available, ahead of any discount.
1 of 5 of the line-up has a cached-input price, which helps chatbots and agents that resend the same instructions. No batch prices are published in our data. 4 of 5 accept images as input.
FAQ
Amazon API questions
How much does the Amazon API cost?
Amazon's 5 models range from $0.035 to $2.50 per million input tokens, and output costs more than input on almost every model. The exact bill depends on your token volumes, which you can estimate in the LLM cost calculator.
What is Amazon's cheapest model?
By blended price (three parts input to one part output) it is Nova Micro 1.0, at $0.035 input and $0.14 output per million tokens. The most expensive is Nova Premier 1.0.
Which Amazon model has the largest context window?
Nova 2 Lite, with 1,000,000 tokens per request.
Does Amazon offer prompt caching or batch discounts?
In our data, 1 of 5 of Amazon's models have a published cached-input price and none have a published batch price. Both can cut costs substantially for repeated prompts or work that can wait.