Nova Micro — API Pricing & Benchmarks
Nova Micro is Amazon's small model, released in 2024-12. The API costs $0.04 per 1M input tokens and $0.14 per 1M output tokens ($0.06 blended at a 3:1 ratio). It supports a 128K-token context window. On the independently measured Artificial Analysis Intelligence Index it scores 4.4, ranking #68 of 68 models tracked on this site, with a median output speed of 288 tokens/sec.
Explore provider routes and additional benchmark sources for Nova Micro
| Provider | Amazon |
| Input price / 1M tokens | $0.04 |
| Output price / 1M tokens | $0.14 |
| Cached input / 1M tokens | — |
| Blended price (3:1) | $0.06 |
| Context window | 128K |
| Max output tokens | 10K |
| Knowledge cutoff | 2024-10 |
| License | proprietary |
| Input modalities | T |
| Output speed (tok/s) | 288 |
| Released | 2024-12 |
| Artificial Analysis Intelligence Index | 4.4 |
| GPQA Diamond | 35.8% |
| Humanity's Last Exam | 4.6% |
Where Nova Micro fits
On a blended 3:1 basis Nova Micro costs $0.06 per 1M tokens, cheaper than 99% of the 80 priced models in this index. It is built for high-volume, latency-sensitive work — classification, extraction, routing and autocomplete — where per-token price matters more than peak intelligence. Measured output speed of 288 tokens/sec is well above the index median of 104, making it suitable for interactive, user-facing use.
Price history
| Period | Input $/1M | Output $/1M | Cached $/1M |
|---|---|---|---|
| 2026-07-18 → current | $0.04 | $0.14 | — |
No list-price changes recorded since tracking began. Full dataset: price-history.json (CC BY 4.0).
Alternatives at a similar price
- Command R7B (Cohere) — $0.07/1M blended
- GPT-4.1 nano (OpenAI) — $0.18/1M blended, AA Index 9.6
- Qwen3.8-Flash (Alibaba Qwen) — $0.23/1M blended, AA Index 55.8
- GLM-5.3-Flash (Zhipu AI (Z.ai)) — $0.24/1M blended, AA Index 57.5
About Amazon
Amazon's Nova models are built for AWS Bedrock, prioritizing price and throughput over peak benchmark scores. Nova Micro is among the cheapest models tracked in this index.