GPT-4.1 Nano

JSON →
openai llm
textimage

Smallest and fastest GPT-4.1 variant designed for low-latency, cost-efficient tasks with strong instruction following.

context window 1.0M tokens
max output 33K tokens
input price $0.1 / 1M tokens
output price $0.4 / 1M tokens
tool-usejson-modevisionprompt-cachingstreamingreasoningcode-generationfunction-calling
releasedApr 2025
knowledge cutoffMar 2025
full doc /v1/models/gpt-4.1-nano