OpenAI model product
1 family.
Updated Aug 12, 2026. Default version: GPT-4.1 nano
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for GPT-4.1 nano.
| OpenAI-MRCR: 2 needle 1M | 0.1 | 5 | 5 | 0.0% | C | |
| Internal API instruction following (hard) | 0.3 | 6 | 7 | 16.7% | C | |
| ComplexFuncBench | 0.1 | 7 | 7 | 0.0% | C | |
| Graphwalks parents >128k | 0.1 | 7 | 7 | 0.0% | C | |
| OpenAI-MRCR: 2 needle 128k | 0.4 | 7 | 9 | 25.0% | C | |
| Aider-Polyglot Edit | 0.1 | 10 | 10 | 0.0% | C | |
| COLLIE | 0.4 | 10 | 10 | 0.0% | C | |
| Graphwalks BFS <128k | 0.3 | 11 | 11 | 0.0% | C | |
| Graphwalks BFS >128k | 0.0 | 11 | 11 | 0.0% | C | |
| Graphwalks parents <128k | 0.1 | 11 | 11 | 0.0% | C | |
| CharXiv-D | 0.7 | 16 | 16 | 0.0% | C | |
| Multi-IF | 0.6 | 20 | 20 | 0.0% | C | |
| Aider-Polyglot | 0.1 | 22 | 22 | 0.0% | C | |
| TAU-bench Airline | 0.1 | 23 | 23 | 0.0% | C | |
| TAU-bench Retail | 0.2 | 25 | 25 | 0.0% | C | |
| Multi-Challenge | 0.1 | 29 | 29 | 0.0% | C | |
| MathVista | 0.6 | 31 | 39 | 21.1% | C | |
| MMMLU | 0.7 | 46 | 49 | 6.3% | C | |
| CharXiv-R | 0.4 | 47 | 48 | 2.1% | C | |
| MMMU | 0.6 | 51 | 63 | 19.4% | C | |
| AIME 2024 | 0.3 | 52 | 53 | 1.9% | C | |
| IFEval | 0.7 | 60 | 65 | 7.8% | C | |
| MMLU | 0.8 | 62 | 100 | 38.4% | C | |
| GPQA | 0.5 | 178 | 234 | 24.0% | C |
Preference and agent-evaluation results for the default version.
| vision | overall | 117 | 1063.5 | 1,211 | N/A | |
| vision style control | overall | 117 | 1089.5 | 1,211 | N/A | |
| text style control | overall | 230 | 1322.2 | 6,103 | N/A | |
| text | overall | 234 | 1284.8 | 6,103 | N/A |
Official vendor API pricing appears first, followed by individual provider offers.
| Impossibl | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| NanoGPT | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| NEAR AI Cloud | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| OrcaRouter | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| Kilo Gateway | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| Merge Gateway | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| Vercel AI Gateway | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| OpenRouter | openai/gpt-4.1-nano | global | $0.10 | $0.40 | 1M | |
| OpenAI | gpt-4.1-nano | global | $0.10 | $0.40 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT-4.1 nano | 4.3 | N/A | 1M | 32.8K | No | Proprietary |
Key information about GPT-4.1-nano and its available data.
1 family. It delivers exceptional performance at a small size with its 1 million token context window. Ideal for tasks like classification or autocompletion.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about GPT-4.1-nano.
GPT-4.1-nano's default version was released on Apr 14, 2025.
GPT-4.1-nano's official API price is $0.10 per million input tokens and $0.40 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.10 input and $0.40 output via Impossibl.
GPT-4.1-nano was created by OpenAI.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
9 provider offerings are linked to the default version.
Nearby ranked alternatives include Phi 3.5 MoE, GPT-4, Qwen2.5 Coder 32B.