Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing documents, extracting information from v…
Model details →Amazon: Nova 2 Lite vs Auto Router
Auto Router wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used, visit [Activity](/activity), or read the `model` attribute of the respon…
Model details →Side-by-side comparison
| Capability | Amazon: Nova 2 Lite | Auto Router | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 1M | 2M | 🏆 Auto Router |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.30 | $-1000000.00 | 🏆 Auto Router |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $2.50 | $-1000000.00 | 🏆 Auto Router |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Amazon: Nova 2 Lite better than Auto Router?
Auto Router wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Amazon: Nova 2 Lite and Auto Router?
Input: $0.30 vs $-1000000.00 per 1M tokens. Output: $2.50 vs $-1000000.00 per 1M tokens.
What context windows do Amazon: Nova 2 Lite and Auto Router support?
Amazon: Nova 2 Lite supports up to 1M tokens. Auto Router supports up to 2M tokens.
Do both Amazon: Nova 2 Lite and Auto Router support tool calling?
Amazon: Nova 2 Lite: yes. Auto Router: yes.