Nova Pro Reasoning: pricing, context window and benchmarks
Nova Pro Reasoning is a multimodal model from Amazon. It offers a 200,000-token context window, costs $13.48 per million input tokens and $65.09 per million output tokens, and averages 79.4 across the index's benchmark suite.
Pricing
Nova Pro Reasoning costs $13.48 per million input tokens and $65.09 per million output tokens. A blended 3:1 input-to-output mix works out to about $26.38 per million tokens. Cached input is listed at $1.44 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $13.48 | per 1M tokens |
| Output | $65.09 | per 1M tokens |
| Cached input | $1.44 | per 1M tokens |
| Blended 3:1 | $26.38 | estimate per 1M tokens |
| 1M in + 1M out | $78.57 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 79.5 | 197 | 67th | |
| GPQA Diamond | 73.4 | 192 | 68th | |
| SWE-bench Verified | 70.1 | 109 | 82th | |
| HumanEval | 83.4 | 150 | 75th | |
| MATH-500 | 84.2 | 122 | 80th | |
| AIME 2025 | 74.1 | 179 | 70th | |
| LiveCodeBench | 74.2 | 104 | 83th | |
| IFEval | 87.4 | 124 | 79th | |
| TruthfulQA | 79.9 | 183 | 70th | |
| HellaSwag | 89.0 | 112 | 81th | |
| MMMU | 78.6 | 84 | 86th | |
| Arena Elo | 1415.8 | 165 | 73th |
What Nova Pro Reasoning is good for
Nova Pro Reasoning is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $13.48 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $13.48 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Qwen3-Coder | Alibaba Cloud | 200000 | $4.94 | 79.5 |
| Claude Haiku 4.5 | Anthropic | 1000000 | $13.86 | 79.4 |
| Doubao 1.5 Pro Turbo | ByteDance | 128000 | $13.81 | 79.4 |
| MiniMax-M2 Instruct | MiniMax | 128000 | $5.11 | 79.4 |
| Nova Pro | Amazon | 32768 | $12.75 | 79.4 |
| Nova Pro Reasoning | Amazon | 200000 | $13.48 | 79.4 |
FAQ
How much does Nova Pro Reasoning cost?
Nova Pro Reasoning is listed at $13.48 per million input tokens and $65.09 per million output tokens. Cached input is $1.44 per million tokens. A blended 3:1 input-to-output mix is about $26.38 per million tokens.
What is the context window of Nova Pro Reasoning?
Nova Pro Reasoning has a context window of 200,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Nova Pro Reasoning open weights?
No. Nova Pro Reasoning is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Nova Pro Reasoning score on benchmarks?
Nova Pro Reasoning averages 79.4 across the scored benchmarks in this index, ranking #139 of 600 models. Its strongest relative result is Arena Elo at 1415.8.
What is Nova Pro Reasoning best for?
Nova Pro Reasoning is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $13.48 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.