GPT-4.1 Nano
GPT-4.1 Nano is a large language model made by OpenAI, added to the catalog on 14 Apr 2025. It has a context window of 1,047,576 tokens and costs $0.10 per 1M input tokens and $0.40 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: speed up text classification tasks, enhance autocompletion systems and develop low-latency applications.
Price checked · source: OpenRouter
What GPT-4.1 Nano is
Released in April 2025, OpenAI's GPT-4.1 Nano is designed for tasks requiring low latency. With a context window of 1,047,576 tokens, this model processes both text and image inputs, outputting text. It's versatile for applications like classification and autocompletion, offering a balanced performance with scores of 80.1% on MMLU and 50.3% on GPQA. GPT-4.1 Nano is a practical choice for developers needing efficient processing in a compact form.
Key features
- 1,047,576 token context window
- Processes text and image inputs
- Outputs text
- Scores 80.1% on MMLU
- Compact and efficient design
Typical uses
- Speed up text classification tasks
- Enhance autocompletion systems
- Develop low-latency applications
GPT-4.1 Nano pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.10 | $0.05 |
| Output, per 1M tokens | $0.40 | $0.20 |
| Cached input read, per 1M tokens | $0.03 | $0.0125 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-4.1-nano:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 14 Apr 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0028 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0038 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.016 |
GPT-4.1 Nano specifications
| Model id | openai/gpt-4.1-nano |
|---|---|
| Version | gpt-4.1-nano-2025-04-14 |
| Context window | 1,047,576 tokensAbout 785,682 English words |
| Max output | 942,818 tokens |
| Knowledge cutoff | 2024-06-30 |
| Added to catalog | 14 Apr 2025 |
| Input types | image, text, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
Artificial Intelligence (AI) is poised to revolutionize work, leisure, and creativity in profound ways. In the workplace, AI can automate routine tasks, allowing employees to focus on strategic, innovative, and high-value activities. This shift enhances productivity and job satisfaction while reducing burnout. During leisure time, AI-driven entertainment, such as personalized content recommendations and immersive virtual realities, offers more tailored and engaging experiences. It can also facilitate lifelong learning through intelligent tutoring systems, making education accessible and adaptable to individual needs. In the realm of creativity, AI acts as a collaborative partner, assisting artists, musicians, and writers in generating new ideas and refining their work. It democratizes creative expression by providing advanced tools accessible to everyone, regardless of skill level. Overall, AI’s integration promises a future where work is more meaningful, leisure more enjoyable, and human creativity expanded beyond current limits—paving the way for a more innovative and fulfilling society.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.
Compare GPT-4.1 Nano
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.