OpenAI model product
1 mini provides a balance between intelligence, speed, and cost.
Updated Aug 12, 2026. Default version: GPT-4.1 mini
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 mini.
| OpenAI-MRCR: 2 needle 1M | 0.3 | 4 | 5 | 25.0% | C | |
| ComplexFuncBench | 0.5 | 5 | 7 | 33.3% | C | |
| Internal API instruction following (hard) | 0.5 | 5 | 7 | 33.3% | C | |
| OpenAI-MRCR: 2 needle 128k | 0.5 | 5 | 9 | 50.0% | C | |
| CharXiv-D | 0.9 | 6 | 16 | 66.7% | C | |
| Graphwalks parents <128k | 0.6 | 6 | 11 | 50.0% | C | |
| Graphwalks parents >128k | 0.1 | 6 | 7 | 16.7% | C | |
| Aider-Polyglot Edit | 0.3 | 8 | 10 | 22.2% | C | |
| Graphwalks BFS <128k | 0.6 | 8 | 11 | 30.0% | C | |
| COLLIE | 0.5 | 9 | 10 | 11.1% | C | |
| MathVista | 0.7 | 9 | 39 | 79.0% | C | |
| Graphwalks BFS >128k | 0.1 | 10 | 11 | 10.0% | C | |
| Multi-IF | 0.7 | 17 | 20 | 15.8% | C | |
| Aider-Polyglot | 0.3 | 19 | 22 | 14.3% | C | |
| TAU-bench Airline | 0.4 | 20 | 23 | 13.6% | C | |
| TAU-bench Retail | 0.6 | 22 | 25 | 12.5% | C | |
| MMLU | 0.9 | 23 | 100 | 77.8% | C | |
| Multi-Challenge | 0.4 | 26 | 29 | 10.7% | C | |
| MMMU | 0.7 | 27 | 63 | 58.1% | C | |
| HMMT 2025 | 0.3 | 31 | 33 | 6.3% | C | |
| CharXiv-R | 0.6 | 38 | 48 | 21.3% | C | |
| MMMLU | 0.8 | 40 | 49 | 18.8% | C | |
| IFEval | 0.8 | 41 | 65 | 37.5% | C | |
| AIME 2024 | 0.5 | 47 | 53 | 11.5% | C | |
| Humanity's Last Exam | 0.0 | 93 | 93 | 0.0% | C | |
| SWE-Bench Verified | 0.2 | 102 | 105 | 2.9% | C | |
| AIME 2025 | 0.4 | 109 | 114 | 4.4% | C | |
| GPQA | 0.7 | 151 | 234 | 35.6% | C |
Preference and agent-evaluation results for the default version.
| vision style control | overall | 69 | 1202.6 | 40,833 | N/A | |
| vision | overall | 83 | 1182.5 | 40,833 | N/A | |
| text style control | overall | 161 | 1382.8 | 39,419 | N/A | |
| text | overall | 186 | 1340.6 | 39,419 | N/A |
Official vendor API pricing appears first, followed by individual provider offers.
| Helicone | gpt-4.1-mini-2025-04-14 | global | $0.40 | $1.6 | 1M | |
| Impossibl | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| NanoGPT | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| NEAR AI Cloud | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| Ofox | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| OrcaRouter | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| Kilo Gateway | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| Merge Gateway | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| Vercel AI Gateway | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| OpenRouter | openai/gpt-4.1-mini | global | $0.40 | $1.6 | 1M | |
| OpenAI | gpt-4.1-mini | global | $0.40 | $1.6 | 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 mini | 24.8 | N/A | 1M | 32.8K | No | Proprietary |
Key information about GPT-4.1-mini and its available data.
1 mini provides a balance between intelligence, speed, and cost. It's a significant leap in small model performance, even beating GPT-4o in many benchmarks while reducing latency and cost.
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-mini.
GPT-4.1-mini's default version was released on Apr 14, 2025.
GPT-4.1-mini's official API price is $0.40 per million input tokens and $1.6 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.40 input and $1.6 output via Helicone.
GPT-4.1-mini 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.
12 provider offerings are linked to the default version.
Nearby ranked alternatives include Llama 4 Maverick, QwQ 32B, Qwen3 VL 8B.