Skip to content
AI IntelligenceJun 30, 2026AI Intelligence
Article

OpenAI has cut inference costs for its AI models by more than half, according to a report.

The optimizations were applied to ChatGPT, reducing the number of Nvidia GPUs needed to just a few hundred at times.

Data Cube AI EditorialSource: The Decoder
01

Source Brief

OpenAI has cut inference costs for its AI models by more than half, according to a report. The optimizations were applied to ChatGPT, reducing the number of Nvidia GPUs needed to just a few hundred at times.

02