Amazon model product
Amazon Nova 2 Lite is a low-latency, cost-effective multimodal reasoning model for everyday workloads.
Updated Aug 17, 2026. Default version: Nova 2 Lite
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Nova 2 Lite.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkLongCodeBench | Score84.0% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkQVHighlights | Score77.2% | Rank01 | Participants3 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score76.6% | Rank02 | Participants29 | Percentile96.4% | EvidenceC | Evaluated |
| BenchmarkRealKIE-FCC | Score62.1% | Rank02 | Participants3 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkOCRBench_V2 | Score56.1% | Rank07 | Participants7 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score64.8% | Rank08 | Participants23 | Percentile68.2% | EvidenceC | Evaluated |
| BenchmarkBFCL-V4 | Score60.3% | Rank09 | Participants15 | Percentile42.9% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score76.5% | Rank14 | Participants26 | Percentile48.0% | EvidenceC | Evaluated |
| BenchmarkScreenSpot | Score83.3% | Rank16 | Participants16 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score32.5% | Rank17 | Participants25 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score70.8% | Rank19 | Participants34 | Percentile45.5% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score71.0% | Rank22 | Participants75 | Percentile71.6% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score76.0% | Rank23 | Participants35 | Percentile35.3% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score24.6% | Rank33 | Participants33 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score91.0% | Rank44 | Participants115 | Percentile62.3% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score61.8% | Rank47 | Participants68 | Percentile31.3% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score80.9% | Rank52 | Participants134 | Percentile61.6% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score64.5% | Rank79 | Participants111 | Percentile29.1% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score79.6% | Rank94 | Participants239 | Percentile60.9% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryoverall | Rank142 | Rating / score1380.1 | Votes11,833 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank172 | Rating / score1362.1 | Votes12,298 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank214 | Rating / score1335.7 | Votes12,298 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNova | Provider model IDnova-2-lite-v1 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderOpenRouter | Provider model IDamazon/nova-2-lite-v1 | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDamazon/nova-2-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDamazon.nova-2-lite-v1:0 | Regionglobal | Input / 1M$0.33 | Output / 1M$2.75 | Context128K | Updated |
| ProviderCortecs | Provider model IDnova-2-lite | Regionglobal | Input / 1M$0.373 | Output / 1M$3.14 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Nova 2 Lite. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionNova 2 Lite | Released | LLMBoard42.4 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Nova 2 Lite and its available data.
Amazon Nova 2 Lite is a low-latency, cost-effective multimodal reasoning model for everyday workloads.
It processes text, images, and video to generate text output, with hybrid reasoning controls that let developers toggle extended thinking on or off and adjust depth (low, medium, high) to balance accuracy, speed, and cost. 5 Flash on most standard benchmarks.
Data as of 2026-08-17.
Common questions about Nova 2 Lite.
Nova 2 Lite's default version was released on Dec 2, 2025.
Nova 2 Lite's official API price is $0.33 per million input tokens and $2.75 per million output tokens via Amazon Bedrock. The lowest tracked third-party offer starts at $0.30 input and $2.5 output via OpenRouter.
Nova 2 Lite was created by Amazon.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
5 provider offerings are linked to the default version.
Nearby ranked alternatives include GPT-OSS-120B, Step3 VL 10B, Qwen3 VL 235B A22B.