GPT-5.4 Nano

JSON →
openai llm
text

The smallest and fastest model in the GPT-5.4 family, designed for simple tasks and edge deployment.

context window 272K tokens
max output 128K tokens
input price $0.2 / 1M tokens
output price $1.25 / 1M tokens
streamingjson-modefunction-callingtool-usevisionprompt-cachingreasoning
releasedMar 2026
knowledge cutoffDec 2025
full doc /v1/models/gpt-5.4-nano