Overview

• OpenAI has introduced three new models—GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano—available exclusively through its API for developers.
• The models feature a 1 million token context window, enabling them to process significantly larger inputs compared to previous versions.
• GPT-4.1 delivers 21% better coding performance than GPT-4o and 27% better than GPT-4.5 on industry benchmarks, while being 26% more cost-effective.
• OpenAI plans to retire the GPT-4.5 Preview from its API by July 14, 2025, positioning GPT-4.1 as the preferred replacement.
• These models are optimized for real-world applications, with enhanced performance in coding, instruction adherence, and powering AI agents.