Context Window
—
Input Price/1M
$0.06
Output Price/1M
$0.24
Parameters
—
Speed
219 tok/s
Latency (TTFT)
621ms
Nova Lite results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 1.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LiveCodeBench | 17.0 | 100.0 | Artificial Analysis official API |
| SciCode | 14.0 | 100.0 | — |
| AA Coding Index | 5.1 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 59.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 18.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MATH-500 | 76.5 | 100.0 | Artificial Analysis official API |
| AA Math Index | 7.0 | 100.0 | Artificial Analysis official API |
| AIME 2025 | 7.0 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU Pro | 59.0 | 100.0 | Artificial Analysis official API |
| GPQA Diamond | 43.0 | 100.0 | Artificial Analysis official API |
| IFBench | 34.0 | 100.0 | — |
| HLE | 5.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 18.0 | 100.0 | — |
Nova Lite is an AI model developed by Amazon, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Amazon's cloud API.
Nova Lite is usage-based, priced at $0.06/1M input tokens and $0.24/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Nova Lite was evaluated on 15 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show moderate performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Nova Lite specializes in text, offering advanced capabilities for creating and processing text content.
In the 2026 AI model ecosystem, Nova Lite competes directly with similarly capable models. Amazon competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Nova Lite is an AI model developed by Amazon. It is a text model.
Nova Lite costs $0.06/1M input tokens and $0.24/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
In available benchmarks, Nova Lite scored: Terminal-Bench Hard: 1/100, LiveCodeBench: 17/100, SciCode: 14/100. See the full table above for a detailed comparison.
No, Nova Lite is a proprietary model from Amazon. It is available via cloud API. For open source alternatives, check our open source model ranking.
Nova Lite excels at general-purpose language tasks.
Last updated: June 01, 2026 • View methodology →