We’re excited to share the launch of the subsequent technology of the GPT-4o mannequin collection with GPT-4.1, 4.1-mini, and 4.1-nano to Microsoft Azure OpenAI Service.
We’re excited to share the launch of the subsequent iteration of the GPT mannequin collection with GPT-4.1, 4.1-mini, and 4.1-nano to Microsoft Azure OpenAI Service and GitHub. The GPT-4.1 fashions deliver improved capabilities and vital developments in coding, instruction following, and long-context processing that’s crucial for builders. We’re additionally excited to announce fine-tuning assist for GPT-4.1 and 4.1-mini, permitting builders to additional customise the fashions for his or her particular enterprise wants.
What’s GPT-4.1?
GPT-4.1 is the most recent iteration of the GPT-4o mannequin, educated to excel at coding and instruction-following duties. This mannequin will enhance the standard of agentic workflows and speed up the productiveness of builders throughout all situations.
Key options of GPT-4.1
GPT-4.1 brings a number of notable enhancements:
- Enhanced coding and instruction following: The mannequin is optimized for higher dealing with of complicated technical and coding issues. It generates cleaner, less complicated front-end code, precisely identifies essential adjustments in present code, and persistently produces outputs that compile and run efficiently.
- Lengthy context mannequin: GPT-4.1 helps a million token inputs, permitting it to course of and perceive in depth context in a single interplay. This functionality is especially helpful for duties requiring detailed and nuanced understanding in addition to multi-step brokers that improve context as they function.
- Improved instruction following: The mannequin excels at following detailed directions, particularly brokers containing a number of requests. It’s extra intuitive and collaborative, making it simpler to work with for varied purposes.
Mannequin capabilities
Along with the post-training enhancements and lengthy context assist, GPT-4.1 retains the identical API capabilities because the GPT-4o mannequin household, together with instrument calling and structured outputs.
| Mannequin | Reasoning & Accuracy | Price & Effectivity | Context Size |
| GPT-4.1 | Highest | Greater Price | 1M |
| GPT-4.1-mini | Balanced | Balanced | 1M |
| GPT-4.1-nano | Decrease | Lowest Price | 1M |
Coming quickly: Positive-tune GPT-4.1 to your small business wants
Later this week, we’ll be enabling supervised fine-tuning for GPT-4.1 and 4.1-mini, empowering builders to adapt these fashions to their distinctive enterprise necessities. Positive-tuning allows you to securely customise the bottom fashions by yourself datasets, serving to align responses together with your group’s particular tone, area terminology, and process workflows. Positive-tuned fashions are managed and deployed by means of the Azure AI Foundry, providing you with full management over versioning, safety, and scalability.
Discover GPT-4.1 in the present day
GPT-4.1 is now accessible on Azure OpenAI Service, bringing unparalleled developments in AI capabilities. This launch marks a major leap ahead, providing enhanced efficiency, effectivity, and flexibility throughout a wide selection of purposes. Whether or not you’re trying to enhance your customer support chatbot, develop cutting-edge knowledge evaluation instruments, or discover new frontiers in machine studying, GPT-4.1 has one thing to supply.
We invite you to delve into the brand new options and uncover how GPT-4.1 can revolutionize your workflows and purposes. Discover, deploy, and construct purposes utilizing these fashions in the present day in Azure AI Foundry to entry this highly effective instrument and keep forward within the quickly evolving world of AI.