Model Library
AmazonReleased October 29, 2025Nova 2.0 Lite
Amazon · Released October 29, 2025
Intelligence score
12
At a glance
- Intelligence
- 12
- Speed
- 147.5tokens/sec
- Latency
- 1.29stime 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 (Non-reasoning) scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 11). Nova 2.0 Lite (Non-reasoning) generates output at 147.5 tokens per second (based on Amazon's API), which is above average compared to other non-reasoning models in a similar price tier (median: 95.5 t/s). Nova 2.0 Lite (Non-reasoning) costs $0.30 per 1M input tokens (somewhat higher than average, median: $0.20) and $2.50 per 1M output tokens (at the higher end, median: $0.70), based on Amazon's API.
Specifications
Technical specifications
| Model name | Nova 2.0 Lite |
|---|---|
| Provider | Amazon |
| Release date | October 29, 2025 |
| Intelligence score | 12 |
| Speed | 147.5 tokens/sec |
| Latency (TTFT) | 1.29s |
| Input price | $0.30 / 1M tokens |
| Output price | $2.50 / 1M tokens |
| Context window | 2 tokens |
| Parameters | — |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: nova-2-0-lite |
Pricing
Token prices
Price per 1M tokens
Nova 2.0 Lite, 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
FAQ · 18
Frequently asked questions
Nova 2.0 Lite (Non-reasoning) was released on October 29, 2025.
Nova 2.0 Lite (Non-reasoning) was created by Amazon.
Nova 2.0 Lite (Non-reasoning) scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 11).
Nova 2.0 Lite (Non-reasoning) generates output at 147.5 tokens per second (based on Amazon's API), which is above average compared to other non-reasoning models in a similar price tier (median: 95.5 t/s).
Nova 2.0 Lite (Non-reasoning) has a time to first token (TTFT) of 1.29s (based on Amazon's API), which is better than average compared to other non-reasoning models in a similar price tier (median: 1.53s).
Nova 2.0 Lite (Non-reasoning) costs $0.30 per 1M input tokens (somewhat higher than average, median: $0.20) and $2.50 per 1M output tokens (at the higher end, median: $0.70), based on Amazon's API.
Nova 2.0 Lite (Non-reasoning) 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.
No, Nova 2.0 Lite (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Nova 2.0 Lite (Non-reasoning) supports text and image input.
Nova 2.0 Lite (Non-reasoning) supports text output.
Yes, Nova 2.0 Lite (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Nova 2.0 Lite (Non-reasoning) is multimodal. It can process text and image input and generate text output.
Nova 2.0 Lite (Non-reasoning) 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 (Non-reasoning) is proprietary. The model weights are not publicly available.
Nova 2.0 Lite (Non-reasoning) is a proprietary model and Amazon has not disclosed the model size or parameter count.
Nova 2.0 Lite (Non-reasoning) achieves a score of 12 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Nova 2.0 Lite (Non-reasoning) is available via API through 1 provider.
Nova 2.0 Lite (Non-reasoning) is available through 1 API provider.