Model Library
AmazonReleased December 3, 2024Nova Lite
Amazon · Released December 3, 2024
Intelligence score
7
At a glance
- Intelligence
- 7
- Speed
- 171.7tokens/sec
- Latency
- 1.03stime to first token
- Input price
- $0.06per 1M tokens
- Output price
- $0.24per 1M tokens
- Context window
- 300Ktokens
- Parameters
- —
Summary
Comparison summary
Nova Lite scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 5). Nova Lite generates output at 171.7 tokens per second (based on Amazon's API), which is above average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s). Nova Lite costs $0.06 per 1M input tokens (somewhat higher than average, median: $0.05) and $0.24 per 1M output tokens (somewhat higher than average, median: $0.20), based on Amazon's API.
Specifications
Technical specifications
| Model name | Nova Lite |
|---|---|
| Provider | Amazon |
| Release date | December 3, 2024 |
| Intelligence score | 7 |
| Speed | 171.7 tokens/sec |
| Latency (TTFT) | 1.03s |
| Input price | $0.06 / 1M tokens |
| Output price | $0.24 / 1M tokens |
| Context window | 300,000 tokens |
| Parameters | — |
| Reasoning | No |
| Input modalities | image |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: nova-lite |
Pricing
Token prices
Price per 1M tokens
Nova Lite, as listed in the catalog record
- Input$0.06
- Output$0.24
| Token type | Price per 1M |
|---|---|
| Input | $0.06 |
| Output | $0.24 |
Model Intelligence legacy profile: nova-lite
FAQ · 18
Frequently asked questions
Nova Lite was released on December 3, 2024.
Nova Lite was created by Amazon.
Nova Lite scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 5).
Nova Lite generates output at 171.7 tokens per second (based on Amazon's API), which is above average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s).
Nova Lite has a time to first token (TTFT) of 1.03s (based on Amazon's API), which is better than average compared to other non-reasoning models in a similar price tier (median: 1.01s).
Nova Lite costs $0.06 per 1M input tokens (somewhat higher than average, median: $0.05) and $0.24 per 1M output tokens (somewhat higher than average, median: $0.20), based on Amazon's API.
Nova Lite costs $0.06 per 1M input tokens and $0.24 per 1M output tokens (based on Amazon's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.05 per 1M tokens. Pricing may vary by provider.
No, Nova Lite is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Nova Lite supports image input.
Nova Lite supports text only output.
Yes, Nova Lite supports image input and can analyze, describe, and answer questions about images.
No, Nova Lite is not multimodal. It only supports image input.
Nova Lite has a context window of 300k tokens. This determines how much text and conversation history the model can process in a single request.
No, Nova Lite is proprietary. The model weights are not publicly available.
Nova Lite is a proprietary model and Amazon has not disclosed the model size or parameter count.
Nova Lite achieves a score of 7 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Nova Lite is available via API through 1 provider.
Nova Lite is available through 1 API provider.