A lightweight text-only model from Amazon's Nova family designed for low-latency, cost-efficient inference.
- Strengths
- Delivers the lowest latency in the Nova family and handles a substantial 128k token context window.
- Best for
- High-volume applications where speed and efficiency matter more than deep reasoning—like real-time chat, search result ranking, or content filtering.
- Limitations
- As a compact model, it lacks the reasoning depth and nuance of larger models and may struggle with complex multi-step tasks or specialized knowledge.
Input / 1M
$0.035
Output / 1M
$0.14
Cached input / 1M
—
Context window
128K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.035 | $0.14 | — | Imported from OpenRouter | openrouter.ai |