GPT-5.1 Nano: pricing, context window and benchmarks
GPT-5.1 Nano is a multimodal model from OpenAI. It offers a 32,768-token context window, costs $9.56 per million input tokens and $43.06 per million output tokens, and averages 74.1 across the index's benchmark suite.
Pricing
GPT-5.1 Nano costs $9.56 per million input tokens and $43.06 per million output tokens. A blended 3:1 input-to-output mix works out to about $17.94 per million tokens. Cached input is listed at $1.27 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $9.56 | per 1M tokens |
| Output | $43.06 | per 1M tokens |
| Cached input | $1.27 | per 1M tokens |
| Blended 3:1 | $17.94 | estimate per 1M tokens |
| 1M in + 1M out | $52.62 | 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 | 77.0 | 278 | 54th | |
| GPQA Diamond | 71.2 | 235 | 61th | |
| SWE-bench Verified | 63.1 | 251 | 58th | |
| HumanEval | 76.1 | 328 | 45th | |
| MATH-500 | 79.5 | 220 | 63th | |
| AIME 2025 | 66.1 | 328 | 45th | |
| LiveCodeBench | 63.9 | 323 | 46th | |
| IFEval | 82.6 | 257 | 57th | |
| TruthfulQA | 78.1 | 253 | 58th | |
| HellaSwag | 85.5 | 227 | 62th | |
| MMMU | 72.0 | 243 | 60th | |
| Arena Elo | 1378.2 | 280 | 53th |
What GPT-5.1 Nano is good for
GPT-5.1 Nano is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $9.56 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.
Strengths
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $9.56 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-Coder Base | DeepSeek | 32768 | $3.53 | 74.1 |
| GPT-5.1 Nano | OpenAI | 32768 | $9.56 | 74.1 |
| Gemma 3 Instruct | Google DeepMind | 128000 | $3.72 | 74.1 |
| Nova Lite Pro | Amazon | 200000 | $9.69 | 74.1 |
| QwQ Base | Alibaba Cloud | 65536 | $3.68 | 74.1 |
| Reka Flash | Reka AI | 128000 | $9.95 | 74.1 |
FAQ
How much does GPT-5.1 Nano cost?
GPT-5.1 Nano is listed at $9.56 per million input tokens and $43.06 per million output tokens. Cached input is $1.27 per million tokens. A blended 3:1 input-to-output mix is about $17.94 per million tokens.
What is the context window of GPT-5.1 Nano?
GPT-5.1 Nano has a context window of 32,768 tokens and can emit up to 4,096 output tokens per request in this index.
Is GPT-5.1 Nano open weights?
No. GPT-5.1 Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-5.1 Nano score on benchmarks?
GPT-5.1 Nano averages 74.1 across the scored benchmarks in this index, ranking #273 of 600 models. Its strongest relative result is Arena Elo at 1378.2.
What is GPT-5.1 Nano best for?
GPT-5.1 Nano is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $9.56 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.