o3 Nano: pricing, context window and benchmarks
o3 Nano is a mid-range model from OpenAI. It offers a 32,768-token context window, costs $7.78 per million input tokens and $29.81 per million output tokens, and averages 70.6 across the index's benchmark suite.
Pricing
o3 Nano costs $7.78 per million input tokens and $29.81 per million output tokens. A blended 3:1 input-to-output mix works out to about $13.29 per million tokens. Cached input is listed at $1.15 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $7.78 | per 1M tokens |
| Output | $29.81 | per 1M tokens |
| Cached input | $1.15 | per 1M tokens |
| Blended 3:1 | $13.29 | estimate per 1M tokens |
| 1M in + 1M out | $37.59 | 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 | 75.3 | 325 | 46th | |
| GPQA Diamond | 64.8 | 364 | 39th | |
| SWE-bench Verified | 57.9 | 358 | 40th | |
| HumanEval | 72.5 | 377 | 37th | |
| MATH-500 | 74.5 | 339 | 44th | |
| AIME 2025 | 65.6 | 334 | 44th | |
| LiveCodeBench | 60.3 | 365 | 39th | |
| IFEval | 78.2 | 365 | 39th | |
| TruthfulQA | 75.4 | 324 | 46th | |
| HellaSwag | 81.4 | 360 | 40th | |
| MMMU | 70.2 | 295 | 51th | |
| Arena Elo | 1354.5 | 355 | 41th |
What o3 Nano is good for
o3 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 $7.78 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.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Firefunction Turbo | Fireworks AI | 32768 | $8.44 | 70.7 |
| Arctic Instruct | Snowflake | 65536 | $2.83 | 70.6 |
| Nova Pro Mini | Amazon | 16384 | $7.74 | 70.6 |
| OLMo 2 Chat | Allen Institute for AI | 16384 | $2.94 | 70.6 |
| o3 Nano | OpenAI | 32768 | $7.78 | 70.6 |
| GPT-4.1 Nano | OpenAI | 32768 | $7.42 | 70.5 |
FAQ
How much does o3 Nano cost?
o3 Nano is listed at $7.78 per million input tokens and $29.81 per million output tokens. Cached input is $1.15 per million tokens. A blended 3:1 input-to-output mix is about $13.29 per million tokens.
What is the context window of o3 Nano?
o3 Nano has a context window of 32,768 tokens and can emit up to 16,384 output tokens per request in this index.
Is o3 Nano open weights?
No. o3 Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does o3 Nano score on benchmarks?
o3 Nano averages 70.6 across the scored benchmarks in this index, ranking #356 of 600 models. Its strongest relative result is Arena Elo at 1354.5.
What is o3 Nano best for?
o3 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 $7.78 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.