Amazon model product
A text-only model that delivers lowest-latency responses at very low cost while maintaining strong performance on core language tasks. Optimized for speed and efficiency while preserving high accuracy on key benchmarks.
Updated Aug 10, 2026. Default version: Nova Micro
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 Micro.
| CRAG | 0.4 | 3 | 3 | 0.0% | C | |
| FinQA | 0.7 | 3 | 3 | 0.0% | C | |
| Translation en→Set1 COMET22 | 0.9 | 3 | 3 | 0.0% | C | |
| Translation en→Set1 spBleu | 0.4 | 3 | 3 | 0.0% | C | |
| Translation Set1→en COMET22 | 0.9 | 3 | 3 | 0.0% | C | |
| Translation Set1→en spBleu | 0.4 | 3 | 3 | 0.0% | C | |
| SQuALITY | 0.2 | 5 | 5 | 0.0% | C | |
| BBH | 0.8 | 9 | 12 | 27.3% | C | |
| ARC-C | 0.9 | 11 | 34 | 69.7% | C | |
| BFCL | 0.6 | 11 | 11 | 0.0% | C | |
| DROP | 0.8 | 15 | 30 | 51.7% | C | |
| GSM8k | 0.9 | 20 | 48 | 59.6% | C | |
| IFEval | 0.9 | 35 | 65 | 46.9% | C | |
| MATH | 0.7 | 43 | 71 | 40.0% | C | |
| HumanEval | 0.8 | 49 | 76 | 36.0% | C | |
| MMLU | 0.8 | 71 | 100 | 29.3% | C | |
| GPQA | 0.4 | 206 | 233 | 11.6% | 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-micro-v1:0 | global | $0.035 | $0.14 | 128K | |
| Vercel AI Gateway | amazon/nova-micro | global | $0.035 | $0.14 | 128K |
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 Micro | 36.3 | N/A | 128K | 128K | No | Proprietary |
A concise description based on the published model registry.
A text-only model that delivers lowest-latency responses at very low cost while maintaining strong performance on core language tasks. Optimized for speed and efficiency while preserving high accuracy on key 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 Micro.
Nova Micro's default version was released on Nov 20, 2024.
Nova Micro's official API price is $0.035 per million input tokens and $0.14 per million output tokens via Amazon Bedrock. The lowest tracked third-party offer starts at $0.035 input and $0.14 output via Vercel AI Gateway.
Nova Micro is published under Amazon in the model registry.
The default version has a 128K 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 Qwen2 72B, Phi 4, Gemini 1.5 Flash.