Nova 2 Lite — API Pricing & Benchmarks
Nova 2 Lite is Amazon's mid reasoning model, released in 2025-12. The API costs $0.30 per 1M input tokens and $2.50 per 1M output tokens ($0.85 blended at a 3:1 ratio), with cached input at $0.07. It supports a 1M-token context window. On the independently measured Artificial Analysis Intelligence Index it scores 20.8, ranking #56 of 68 models tracked on this site, with a median output speed of 191 tokens/sec. Pricing was changed on 2026-07-18 (previously $0.30/$2.50 per 1M tokens).
Explore provider routes and additional benchmark sources for Nova 2 Lite
| Provider | Amazon |
| Input price / 1M tokens | $0.30 |
| Output price / 1M tokens | $2.50 |
| Cached input / 1M tokens | $0.07 |
| Blended price (3:1) | $0.85 |
| Context window | 1M |
| Max output tokens | 66K |
| Knowledge cutoff | 2025-10 |
| License | proprietary |
| Input modalities | T+I+V |
| Output speed (tok/s) | 191 |
| Released | 2025-12 |
| Artificial Analysis Intelligence Index | 20.8 |
| LMArena Elo | 1363 |
| GPQA Diamond | 81.1% |
| Humanity's Last Exam | 11.6% |
Where Nova 2 Lite fits
On a blended 3:1 basis Nova 2 Lite costs $0.85 per 1M tokens, cheaper than 66% of the 80 priced models in this index. It sits in the mid-tier bracket where most production chat, RAG and summarization workloads run: meaningfully cheaper than flagships while keeping most of their capability. Measured output speed of 191 tokens/sec is well above the index median of 104, making it suitable for interactive, user-facing use. Cached input is priced at $0.07 (75% below standard input), which rewards prompt structures with long stable prefixes — see our caching guide.
Price history
| Period | Input $/1M | Output $/1M | Cached $/1M |
|---|---|---|---|
| 2026-07-18 → 2026-07-18 | $0.30 | $2.50 | $0.03 |
| 2026-07-18 → current | $0.30 | $2.50 | $0.07 |
List-price changes recorded by this site. The full dataset is public: price-history.json (CC BY 4.0).
Alternatives at a similar price
- Gemini 3.5 Flash-Lite (Google) — $0.85/1M blended, AA Index 37.4
- Gemini 2.5 Flash (Google) — $0.85/1M blended, AA Index 24.2
- Nova 2 Omni (preview) (Amazon) — $0.85/1M blended, AA Index 21.3
- Mistral Large 3 (Mistral AI) — $0.75/1M blended, AA Index 15.9
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.