The gpt-4.1 series is the latest iteration of the gpt-4o model family. This iteration of models is specifically targeted for better coding and instruction following, making it better at handling complex technical and coding problems.

In addition, it increases the context token limit up to 1M input tokens and provides separate billing for small context (128k) and large (up to 1M) context inputs.

As with the previous gpt-4o model family, it supports a 16k output size and features such as:

• Text, image processing
• JSON Mode
• parallel function calling
• Enhanced accuracy and responsiveness
• Parity with English text and coding tasks compared to GPT-4 Turbo with Vision
• Superior performance in non-English languages and in vision tasks
• Support for enhancements
• Support for complex structured outputs.

• Introducing the gpt-4.1 Series: OpenAI's new flagship multimodal model now in preview on Azure