GPT-5.4 nano is the smallest, fastest, and cheapest model in the GPT-5.4 family, available via the OpenAI API. It is optimized for ultra-low-cost, latency-sensitive workloads where massive scale matters more than peak intelligence — classification, simple chat, lightweight automation, and edge deployments.
Nano is the right choice when you need to call an LLM millions of times per day and only need it to handle relatively simple tasks reliably.