Amazon API Pricing
2 models · From $0.300/1M to $1.25/1M input
The cheapest Amazon model to run is Nova 2.0 Lite at $0.300 input and $2.50 output per 1M tokens. On a RAG answer of 8,000 tokens in and 600 out, Amazon models range from $0.0039 (Nova 2.0 Lite) to $0.016 (Nova 2.0 Pro Reasoning) per request. The largest context window is Nova 2.0 Lite at 1.0M tokens. Count tokens with the Amazon token counter.
| Model | Input /1M | Output /1M | RAG answer |
|---|---|---|---|
| Nova 2.0 Lite | $0.300 | $2.50 | $0.0039 |
| Nova 2.0 Pro Reasoning | $1.25 | $10.00 | $0.016 |