Amazon model product
A low-cost multimodal model that is lightning fast for processing images, video, documents, and text.
Updated Aug 10, 2026. Default version: Nova Lite
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Nova Lite.
| VATEX | 0.8 | 1 | 2 | 100.0% | C | |
| CRAG | 0.4 | 2 | 3 | 50.0% | C | |
| FinQA | 0.7 | 2 | 3 | 50.0% | C | |
| GroundUI-1K | 0.8 | 2 | 2 | 0.0% | C | |
| MM-Mind2Web | 0.6 | 2 | 3 | 50.0% | C | |
| Translation en→Set1 COMET22 | 0.9 | 2 | 3 | 50.0% | C | |
| Translation en→Set1 spBleu | 0.4 | 2 | 3 | 50.0% | C | |
| Translation Set1→en COMET22 | 0.9 | 2 | 3 | 50.0% | C | |
| Translation Set1→en spBleu | 0.4 | 2 | 3 | 50.0% | C | |
| VisualWebBench | 0.8 | 2 | 2 | 0.0% | C | |
| SQuALITY | 0.2 | 4 | 5 | 25.0% | C | |
| BBH | 0.8 | 6 | 12 | 54.5% | C | |
| EgoSchema | 0.7 | 6 | 9 | 37.5% | C | |
| ARC-C | 0.9 | 8 | 34 | 78.8% | C | |
| TextVQA | 0.8 | 8 | 15 | 50.0% | C | |
| BFCL | 0.7 | 9 | 11 | 20.0% | C | |
| ChartQA | 0.9 | 10 | 24 | 60.9% | C | |
| DROP | 0.8 | 12 | 30 | 62.1% | C | |
| GSM8k | 0.9 | 15 | 48 | 70.2% | C | |
| DocVQA | 0.9 | 16 | 26 | 40.0% | C | |
| IFEval | 0.9 | 19 | 65 | 71.9% | C | |
| LVBench | 0.4 | 24 | 24 | 0.0% | C | |
| MATH | 0.7 | 31 | 71 | 57.1% | C | |
| HumanEval | 0.9 | 39 | 76 | 49.3% | C | |
| MMMU | 0.6 | 50 | 63 | 21.0% | C | |
| MMLU | 0.8 | 59 | 100 | 41.4% | C | |
| GPQA | 0.4 | 199 | 233 | 14.7% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| Amazon Bedrock | amazon.nova-lite-v1:0 | global | $0.06 | $0.24 | 300K | |
| Vercel AI Gateway | amazon/nova-lite | global | $0.06 | $0.24 | 300K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Nova Lite | 49.2 | N/A | 300K | 2K | No | Proprietary |
A concise description based on the published model registry.
A low-cost multimodal model that is lightning fast for processing images, video, documents, and text.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
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 published LLMBoard score.
Common questions about Nova Lite.
Nova Lite's default version was released on Nov 20, 2024.
Nova Lite's official API price is $0.06 per million input tokens and $0.24 per million output tokens via Amazon Bedrock. The lowest tracked third-party offer starts at $0.06 input and $0.24 output via Vercel AI Gateway.
Nova Lite is published under Amazon in the model registry.
The default version has a 300K token context window.
No. The default version is not marked as having publicly available weights.
2 published provider offerings are linked to the default version.
Nearby ranked alternatives include GPT-4-Turbo, Mercury 2, Phi 4 Reasoning Plus.