GPT-4.1 Nano moves to version gpt-4.1-nano-2025-04-14
OpenAI updates its lightweight model architecture for improved optimization and stability.
Version now gpt-4.1-nano-2025-04-14 (was gpt-4.1-nano) — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.
OnAirToday
Newsroom

The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-4.1 Nano (version gpt-4.1-nano-2025-04-14): Version now gpt-4.1-nano-2025-04-14 (was gpt-4.1-nano).
GPT-4.1 nano is OpenAI's small, low-latency GPT-4.1 model, supporting text and image inputs with text outputs. Its documented API configuration provides a 1,047,576-token context window, with standard pricing of $0.10 per million input tokens and $0.40 per million output tokens.
What changed in this review:
- Identified the dated API snapshot as gpt-4.1-nano-2025-04-14; gpt-4.1-nano is the model alias.
- Specified the documented context window as 1,047,576 tokens.
- OpenAI reports GPQA Diamond at 50.3% and Aider Polyglot at 9.8%.
- Added OpenAI's warning about repeated tool calls when parallel tool calling is enabled.
- Flaws and limitations updated
- Risks and threats updated
Teams building on GPT-4.1 Nano should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.
The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/gpt-4-1-nano.
References:
- https://openai.com/index/gpt-4-1/
- https://platform.openai.com/docs/models/gpt-4.1-nano
- https://platform.openai.com/docs/guides/function-calling
Generated insight by OnAirToday AI
The incremental versioning of GPT-4.1 Nano signals OpenAI's shift toward more frequent, smaller model updates to maintain efficiency and performance standards. This strategy allows developers to integrate granular improvements into resource-constrained environments without necessitating a complete architectural overhaul.

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.