Model Library
AmazonReleased October 29, 2025Nova 2.0 Lite (high)
Amazon · Released October 29, 2025
Intelligence score
18
At a glance
- Intelligence
- 18
- Speed
- 158.0tokens/sec
- Latency
- 23.79stime to first token
- Input price
- $0.30per 1M tokens
- Output price
- $2.50per 1M tokens
- Context window
- 2tokens
- Parameters
- —
Summary
Comparison summary
Nova 2.0 Lite (high) scores 18 on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 15). Nova 2.0 Lite (high) generates output at 158.0 tokens per second (based on Amazon's API), which is above average compared to other reasoning models in a similar price tier (median: 99.0 t/s). Nova 2.0 Lite (high) costs $0.30 per 1M input tokens (somewhat higher than average, median: $0.25) and $2.50 per 1M output tokens (at the higher end, median: $0.87), based on Amazon's API.
Specifications
Technical specifications
| Model name | Nova 2.0 Lite (high) |
|---|---|
| Provider | Amazon |
| Release date | October 29, 2025 |
| Intelligence score | 18 |
| Speed | 158.0 tokens/sec |
| Latency (TTFT) | 23.79s |
| Input price | $0.30 / 1M tokens |
| Output price | $2.50 / 1M tokens |
| Context window | 2 tokens |
| Parameters | — |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: nova-2-0-lite-reasoning |
Pricing
Token prices
Price per 1M tokens
Nova 2.0 Lite (high), as listed in the catalog record
- Input$0.30
- Output$2.50
| Token type | Price per 1M |
|---|---|
| Input | $0.30 |
| Output | $2.50 |
Model Intelligence legacy profile: nova-2-0-lite-reasoning
FAQ · 19
Frequently asked questions
Nova 2.0 Lite (high) was released on October 29, 2025.
Nova 2.0 Lite (high) was created by Amazon.
Nova 2.0 Lite (high) scores 18 on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 15).
Nova 2.0 Lite (high) generates output at 158.0 tokens per second (based on Amazon's API), which is above average compared to other reasoning models in a similar price tier (median: 99.0 t/s).
Nova 2.0 Lite (high) has a time to first token (TTFT) of 23.79s (based on Amazon's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 1.96s).
Nova 2.0 Lite (high) costs $0.30 per 1M input tokens (somewhat higher than average, median: $0.25) and $2.50 per 1M output tokens (at the higher end, median: $0.87), based on Amazon's API.
Nova 2.0 Lite (high) costs $0.30 per 1M input tokens and $2.50 per 1M output tokens (based on Amazon's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.52 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Nova 2.0 Lite (high) generated 220M output tokens, which is at the higher end compared to other reasoning models in a similar price tier (median: 55M).
Yes, Nova 2.0 Lite (high) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Nova 2.0 Lite (high) supports text and image input.
Nova 2.0 Lite (high) supports text output.
Yes, Nova 2.0 Lite (high) supports image input and can analyze, describe, and answer questions about images.
Yes, Nova 2.0 Lite (high) is multimodal. It can process text and image input and generate text output.
Nova 2.0 Lite (high) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
No, Nova 2.0 Lite (high) is proprietary. The model weights are not publicly available.
Nova 2.0 Lite (high) is a proprietary model and Amazon has not disclosed the model size or parameter count.
Nova 2.0 Lite (high) achieves a score of 18 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Nova 2.0 Lite (high) is available via API through 2 providers.
Nova 2.0 Lite (high) is available through 2 API providers.