Amazon model product
Nova Micro
A text-only model that delivers lowest-latency responses at very low cost while maintaining strong performance on core language tasks.
Updated Aug 12, 2026. Default version: Nova Micro
LLMBoard score4.3Nova Micro
Coverage100%17 benchmark families
Context window128KTokens
Official input price$0.035Amazon Bedrock API
Nova Micro Specifications
Technical details for the model's default version.
- Version
- Nova Micro
- Released
- Nov 20, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Nova Micro Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Nova Micro Benchmark Results
Benchmark scores for 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 | 44 | 66 | 33.9% | C | |
| MMLU | 0.8 | 71 | 100 | 29.3% | C | |
| GPQA | 0.4 | 207 | 234 | 11.6% | C |
Nova Micro Arena Results
Preference and agent-evaluation results for the default version.
| text | overall | 285 | 1208.5 | 19,364 | N/A | |
| text style control | overall | 294 | 1240.7 | 19,364 | N/A |
Nova Micro Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.035 input, $0.14 output per 1M
- Official provider
- Amazon Bedrock
- Lowest third-party
- From $0.035 input, $0.14 output per 1M via Vercel AI Gateway
- Tracked offerings
- 2
| 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.
Nova Micro Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Nova Micro | 4.3 | N/A | 128K | 128K | No | Proprietary |
What is Nova Micro?
Key information about Nova Micro and its available data.
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.
Data as of 2026-08-11.
Nova Micro vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Nova Micro
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AM
Nova Lite
Amazon
AM
Nova 2 Sonic
Amazon
AM
Nova Pro
Amazon
AM
Nova 2 Lite
Amazon
AM
Nova 2 Omni
Amazon
AM
Nova 2 Pro
Amazon
FAQ
Common questions about Nova Micro.
When was Nova Micro released?
Nova Micro's default version was released on Nov 20, 2024.
How much does Nova Micro cost?
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.
Who created Nova Micro?
Nova Micro was created by Amazon.
What is the context window for Nova Micro?
The default version has a 128K token context window.
Is Nova Micro open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Nova Micro?
2 provider offerings are linked to the default version.
What models should I compare Nova Micro with?
Nearby ranked alternatives include GPT-4, Qwen2.5 Coder 32B, GPT-4.1-nano.