Vendor
Amazon models
5 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
5
0 routable here
Median list price
$0.85
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Amazon model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Nova 2 Liteamazon/nova-2-lite-v1 | Dec 2, 2025 | 1M | $0.30 | $2.50 | - | reasoning tools |
| Nova Premier 1.0amazon/nova-premier-v1 | Oct 31, 2025 | 1M | $2.50 | $12.5 | - | tools |
| Nova Lite 1.0amazon/nova-lite-v1 | Dec 5, 2024 | 300K | $0.06 | $0.24 | - | tools |
| Nova Micro 1.0amazon/nova-micro-v1 | Dec 5, 2024 | 128K | $0.04 | $0.14 | - | tools |
| Nova Pro 1.0amazon/nova-pro-v1 | Dec 5, 2024 | 300K | $0.80 | $3.20 | - | tools |
Frequently asked
- What is the cheapest Amazon model?
- Nova Micro 1.0 at $0.04 per 1M input tokens and $0.14 per 1M output tokens (vendor list price).
- Which Amazon model has the largest context window?
- Nova 2 Lite accepts 1M tokens of context.
- How do I route to Amazon models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example amazon/nova-2-lite-v1); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Amazon with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Amazon flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.