GPT-4.1 nano

GPT-4.1 nano

Quick answer: GPT-4.1 nano is OpenAI's fastest and cheapest model in the GPT-4.1 family, released April 2025 with a 1-million-token context window, aimed at low-latency tasks like classification and autocompletion.

At a Glance

Where GPT-4.1 nano leads

• Fastest and cheapest model in the GPT-4.1 family, with the same 1M-token context window as its larger siblings
• Scores higher than GPT-4o mini on MMLU (80.1%), GPQA (50.3%), and Aider polyglot coding (9.8%)

Where it lags

• Weakest reasoning/coding performance within the GPT-4.1 family (e.g. 25.0% on Graphwalks BFS vs. 61.7% for GPT-4.1 and GPT-4.1 mini)

Best for: high-volume, low-latency tasks like classification or autocompletion where cost and speed matter more than raw capability.

What GPT-4.1 nano Is

GPT-4.1 nano is the smallest and fastest tier of OpenAI's GPT-4.1 model family, announced alongside GPT-4.1 and GPT-4.1 mini in April 2025. It shares the family's 1-million-token context window and June 2024 knowledge cutoff but trades capability for latency and cost, positioned as OpenAI's fastest and cheapest model at launch.