Nemotron Nano: pricing, context window and benchmarks
Nemotron Nano is a open-weight model from NVIDIA. It offers a 8,192-token context window, costs $2.24 per million input tokens and $8.55 per million output tokens, and averages 66.6 across the index's benchmark suite.
Pricing
Nemotron Nano costs $2.24 per million input tokens and $8.55 per million output tokens. A blended 3:1 input-to-output mix works out to about $3.82 per million tokens. Cached input is listed at $0.30 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.24 | per 1M tokens |
| Output | $8.55 | per 1M tokens |
| Cached input | $0.30 | per 1M tokens |
| Blended 3:1 | $3.82 | estimate per 1M tokens |
| 1M in + 1M out | $10.79 | 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 | 70.5 | 393 | 35th | |
| GPQA Diamond | 65.1 | 357 | 41th | |
| SWE-bench Verified | 54.1 | 392 | 35th | |
| HumanEval | 69.7 | 399 | 34th | |
| MATH-500 | 68.4 | 395 | 34th | |
| AIME 2025 | 60.2 | 387 | 36th | |
| LiveCodeBench | 58.3 | 385 | 36th | |
| IFEval | 74.2 | 402 | 33th | |
| TruthfulQA | 68.8 | 406 | 32th | |
| HellaSwag | 78.0 | 402 | 33th | |
| MMMU | 64.8 | 383 | 36th | |
| Arena Elo | 1334.4 | 382 | 36th |
What Nemotron Nano is good for
Nemotron Nano is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $2.24 per million input tokens (hosted list price) and a 8,192-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $2.24 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- Context window of 8,192 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Molmo Chat | Allen Institute for AI | 32768 | $2.40 | 66.7 |
| Doubao 1.5 Pro Nano | ByteDance | 16384 | $5.78 | 66.6 |
| Nemotron Nano | NVIDIA | 8192 | $2.24 | 66.6 |
| Phi-3.5 Base | Microsoft | 65536 | $2.24 | 66.6 |
| Command A Nano | Cohere | 8192 | $5.90 | 66.3 |
| Nemotron Nano Chat | NVIDIA | 32768 | $2.21 | 66.2 |
FAQ
How much does Nemotron Nano cost?
Nemotron Nano is listed at $2.24 per million input tokens and $8.55 per million output tokens. Cached input is $0.30 per million tokens. A blended 3:1 input-to-output mix is about $3.82 per million tokens.
What is the context window of Nemotron Nano?
Nemotron Nano has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Nemotron Nano open weights?
Yes. Nemotron Nano is listed as an open-weight model under a open weights licence.
How does Nemotron Nano score on benchmarks?
Nemotron Nano averages 66.6 across the scored benchmarks in this index, ranking #390 of 600 models. Its strongest relative result is Arena Elo at 1334.4.
What is Nemotron Nano best for?
Nemotron Nano is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $2.24 per million input tokens (hosted list price) and a 8,192-token context window, it is a practical option for teams that want more control than a closed API allows.