OpenAIReleased Apr 2025Proprietary
GPT-4.1 nano is deprecated and can't be run here; try GPT-6 Luna (69.7% on Vision Evals) instead.
GPT-4.1 nano has no score on the current Vision Evals. On the earlier Vision Evals board (last updated July 9, 2026) it passed 40.3% of visual understanding tasks (#69 of 77). It is a proprietary model from OpenAI, so commercial use follows OpenAI's terms.
This model is deprecated
GPT-4.1 nano and can no longer be run here. Its evaluation results and details remain available for reference. Try GPT-6 Luna instead.
GPT-4.1 nano has been deprecated by its provider and can no longer be evaluated on the current benchmark. The legacy Vision Evals results below are preserved for reference. See the current Vision Evals
| Category | Passed | Score |
|---|---|---|
| Object Understanding | 9 / 14 | 64.3% |
| Spatial Understanding | 8 / 19 | 42.1% |
| Defect Detection | 6 / 15 | 40% |
| Document Understanding | 3 / 9 | 33.3% |
| Object Counting | 1 / 10 | 10% |
| Category | Passed | Score |
|---|---|---|
| VQA & Extraction | 39 / 60 | 65% |
| Text Recognition | 19 / 30 | 63.3% |
| Focused Scene OCR | 54 / 99 | 54.5% |
| License Plate Recognition | 15 / 30 | 50% |
| Handwritten Math | 4 / 10 | 40% |
Scores based on a single evaluation run · Methodology
View all legacy Vision Evals results →GPT-4.1 nano, released by OpenAI in April 2025, is the smallest and most cost-efficient member of the GPT-4.1 family. It is multimodal, supporting both text and image inputs, and retains the family’s extended 1 million-token context window—allowing it to handle large documents or codebases despite its lightweight design. Its training knowledge extends to June 2024.
GPT-4.1 nano costs $0.100 per 1M input tokens and $0.400 per 1M output tokens.
Pricing updated Nov 5, 2026
GPT-4.1 nano is proprietary: the weights are not distributed, and the GPT-4.1 nano license is the vendor's commercial terms of service that you accept when you call the API.
Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.
Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy an open model instead of GPT-4.1 nano, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.
Do not hesitate to reach out with questions for your commercial project. Our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.
Talk to salesLicense information is provided as a guide and is not legal advice.
Estimated cost per task vs. Visual Understanding score, for this model and others ranked near it. Upper-left is the sweet spot (high quality, low cost). Based on Vision Evals (legacy) results.
6 of 7 models plotted · 1 not yet evaluated
| Model | Score | Median tokens | Est. cost / task | Compare |
|---|---|---|---|---|
| Claude Haiku 4.5 | 58.2% | 2.3K | $0.0030 | Compare |
| GPT-5 Nano | 58.2% | 2.7K | $0.0003 | Compare |
| Qwen3.5 397B A17B | 58.2% | 1.5K | $0.0008 | Compare |
| Gemini 2.5 Flash | 55.2% | 476 | $0.0005 | Compare |
| Gemini 2.5 Flash-Lite | 53.7% | 301 | <$0.0001 | Compare |
| GPT-4.1 Nano(this model) | 40.3% | 2.9K | — | — |
| Kimi K2.5 | 35.8% | 2.7K | $0.0027 | Compare |
Other models worth comparing for similar use cases.
Other versions in the same family as GPT-4.1 nano.
Yes. GPT-4.1 nano accepts image input, and on Roboflow's previous vision benchmark it passed 40.3% of visual understanding tasks (#69 of 77) and scored 57.2% on OCR.
No. GPT-4.1 nano has been deprecated by its provider and can no longer be run, so it is not part of Roboflow's current Vision Evals. Its results from the previous benchmark are preserved on this page for reference.