Amazon model product
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. It supports up to 1M tokens of context and matches or exceeds Claude Haiku 4.5, GPT-5 Mini, and Gemini 2.5 Flash on most standard benchmarks.
Updated Aug 10, 2026. Default version: Nova 2 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 2 Lite.
| LongCodeBench | 0.8 | 1 | 2 | 100.0% | C | |
| QVHighlights | 0.8 | 1 | 3 | 100.0% | C | |
| Multi-Challenge | 0.8 | 2 | 29 | 96.4% | C | |
| RealKIE-FCC | 0.6 | 2 | 3 | 50.0% | C | |
| OCRBench_V2 | 0.6 | 7 | 7 | 0.0% | C | |
| Tau2 Airline | 0.6 | 8 | 23 | 68.2% | C | |
| BFCL-V4 | 0.6 | 9 | 13 | 33.3% | C | |
| Tau2 Retail | 0.8 | 14 | 26 | 48.0% | C | |
| IFBench | 0.7 | 15 | 28 | 48.1% | C | |
| ScreenSpot | 0.8 | 16 | 16 | 0.0% | C | |
| Terminal-Bench | 0.3 | 17 | 25 | 33.3% | C | |
| LiveCodeBench | 0.7 | 20 | 73 | 73.6% | C | |
| Tau2 Telecom | 0.8 | 23 | 35 | 35.3% | C | |
| MCP Atlas | 0.2 | 30 | 30 | 0.0% | C | |
| AIME 2025 | 0.9 | 44 | 114 | 62.0% | C | |
| MMMU-Pro | 0.6 | 45 | 65 | 31.3% | C | |
| MMLU-Pro | 0.8 | 48 | 129 | 63.3% | C | |
| SWE-Bench Verified | 0.6 | 73 | 104 | 30.1% | C | |
| GPQA | 0.8 | 89 | 233 | 62.1% | C |
Preference and agent-evaluation signals from published Arena datasets.
| text factuality | russian | 104 | 1372.9 | 668 | N/A | |
| text factuality | industry life and physical and social science | 115 | 1407.6 | 1,216 | N/A | |
| text factuality | creative writing | 121 | 1316.3 | 978 | N/A | |
| text factuality | industry business and management and financial operations | 121 | 1387.2 | 1,439 | N/A | |
| text factuality | industry entertainment and sports and media | 123 | 1327.6 | 1,317 | N/A | |
| text factuality | coding | 124 | 1427.6 | 1,528 | N/A | |
| text factuality | multi turn | 124 | 1360.5 | 1,257 | N/A | |
| text factuality | industry writing and literature and language | 125 | 1352.0 | 1,718 | N/A | |
| text factuality | instruction following | 128 | 1370.9 | 2,163 | N/A | |
| text factuality | hard prompts english | 130 | 1407.7 | 2,057 | N/A | |
| text factuality | longer query | 131 | 1368.7 | 1,853 | N/A | |
| text factuality | industry software and it services | 134 | 1415.2 | 2,969 | N/A | |
| text factuality | english | 136 | 1399.9 | 5,477 | N/A | |
| text factuality | hard prompts | 137 | 1398.1 | 6,162 | N/A | |
| text factuality | exclude ties | 138 | 1356.4 | 8,370 | N/A | |
| text factuality | non english | 138 | 1358.4 | 6,140 | N/A | |
| text factuality | overall | 139 | 1381.0 | 11,749 | N/A | |
| text | french | 144 | 1376.7 | 224 | N/A | |
| text | german | 144 | 1354.5 | 263 | N/A | |
| text | industry business and management and financial operations | 148 | 1368.2 | 2,280 | N/A | |
| text | spanish | 148 | 1361.4 | 201 | N/A | |
| text | industry medicine and healthcare | 151 | 1386.5 | 707 | N/A | |
| text | industry software and it services | 151 | 1394.1 | 4,242 | N/A | |
| text | expert | 152 | 1367.1 | 712 | N/A | |
| text | english | 155 | 1383.4 | 5,744 | N/A | |
| text | industry life and physical and social science | 156 | 1381.6 | 2,059 | N/A | |
| text | coding | 157 | 1388.0 | 2,507 | N/A | |
| text | hard prompts english | 158 | 1381.1 | 3,195 | N/A | |
| text | industry mathematical | 163 | 1370.6 | 582 | N/A | |
| text | polish | 163 | 1324.5 | 411 | N/A | |
| text | hard prompts | 164 | 1365.1 | 6,468 | N/A | |
| text | korean | 164 | 1272.7 | 148 | N/A | |
| text | russian | 167 | 1339.6 | 1,169 | N/A | |
| text | exclude ties | 168 | 1327.1 | 8,750 | N/A | |
| text | overall | 169 | 1362.8 | 12,213 | N/A | |
| text | non english | 170 | 1338.8 | 6,412 | N/A | |
| text | instruction following | 172 | 1335.1 | 3,322 | N/A | |
| text | industry legal and government | 173 | 1355.2 | 887 | N/A | |
| text | chinese | 174 | 1368.4 | 682 | N/A | |
| text | math | 176 | 1360.2 | 825 | N/A | |
| text style control | german | 179 | 1315.1 | 263 | N/A | |
| text | longer query | 180 | 1336.2 | 2,907 | N/A | |
| text style control | expert | 181 | 1361.6 | 712 | N/A | |
| text | industry entertainment and sports and media | 182 | 1306.9 | 2,205 | N/A | |
| text style control | french | 183 | 1345.7 | 224 | N/A | |
| text style control | spanish | 183 | 1330.7 | 201 | N/A | |
| text | industry writing and literature and language | 186 | 1318.8 | 2,743 | N/A | |
| text style control | industry business and management and financial operations | 186 | 1351.0 | 2,280 | N/A | |
| text | multi turn | 187 | 1337.9 | 2,068 | N/A | |
| text style control | coding | 188 | 1395.5 | 2,507 | N/A | |
| text style control | industry software and it services | 191 | 1385.5 | 4,242 | N/A | |
| text style control | hard prompts english | 193 | 1377.5 | 3,195 | N/A | |
| text style control | industry mathematical | 193 | 1349.1 | 582 | N/A | |
| text style control | industry medicine and healthcare | 194 | 1360.0 | 707 | N/A | |
| text style control | polish | 197 | 1283.0 | 411 | N/A | |
| text | creative writing | 198 | 1294.4 | 1,716 | N/A | |
| text style control | instruction following | 198 | 1329.3 | 3,322 | N/A | |
| text style control | math | 198 | 1333.4 | 825 | N/A | |
| text style control | english | 200 | 1361.7 | 5,744 | N/A | |
| text style control | hard prompts | 200 | 1358.7 | 6,468 | N/A | |
| text style control | industry life and physical and social science | 204 | 1356.5 | 2,059 | N/A | |
| text style control | exclude ties | 207 | 1291.9 | 8,750 | N/A | |
| text style control | korean | 207 | 1231.5 | 148 | N/A | |
| text style control | overall | 209 | 1336.6 | 12,213 | N/A | |
| text style control | russian | 210 | 1317.4 | 1,169 | N/A | |
| text style control | chinese | 211 | 1342.4 | 682 | N/A | |
| text style control | longer query | 215 | 1335.5 | 2,907 | N/A | |
| text style control | multi turn | 216 | 1323.8 | 2,068 | N/A | |
| text style control | non english | 216 | 1308.2 | 6,412 | N/A | |
| text style control | industry legal and government | 226 | 1331.3 | 887 | N/A | |
| text style control | industry entertainment and sports and media | 231 | 1282.5 | 2,205 | N/A | |
| text style control | industry writing and literature and language | 233 | 1300.7 | 2,743 | N/A | |
| text style control | creative writing | 246 | 1273.8 | 1,716 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| Nova | nova-2-lite-v1 | global | N/A | N/A | 1M | |
| Vercel AI Gateway | amazon/nova-2-lite | global | $0.30 | $2.5 | 1M | |
| OpenRouter | amazon/nova-2-lite-v1 | global | $0.30 | $2.5 | 1M | |
| Amazon Bedrock | amazon.nova-2-lite-v1:0 | global | $0.33 | $2.75 | 128K | |
| Cortecs | nova-2-lite | global | $0.373 | $3.14 | 1M |
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 2 Lite | 55.1 | N/A | 1M | 65.5K | No | Proprietary |
A concise description based on the published model registry.
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. It supports up to 1M tokens of context and matches or exceeds Claude Haiku 4.5, GPT-5 Mini, and Gemini 2.5 Flash on most standard benchmarks.
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 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 Vercel AI Gateway.
Nova 2 Lite is published under Amazon in the model registry.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
5 published provider offerings are linked to the default version.
Nearby ranked alternatives include MiMo V2 Flash, o3, GLM 4.5 Air.