TY - GEN
T1 - A Comparative Analysis of OpenAI's API Performance
T2 - 6th International Conference on Artificial Intelligence, Robotics, and Control, AIRC 2025
AU - Walee, Nafeeul Alam
AU - Shalan, Atef
AU - Wimmer, Hayden
AU - Kadlec, Christopher
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/5/7
Y1 - 2025/5/7
N2 - Generative AI models have the capability to produce a wide range of new content based on the data they are trained on. These models can generate not just text, but also various types of multimedia content, including images. In recent years, they have become increasingly popular due to their significant impact across multiple fields. They are used in various applications, from text and image generation to music creation, as well as in education, healthcare, robotics, finance, education, autonomous vehicles, and more. However, these models face numerous challenges, such as overfitting the outputs, inconsistency in the results, response time, and token usage. This study presents a comparative analysis of the performance of OpenAI's API, focusing on insights gleaned from AI response statistics. The evaluation encompasses various performance insights on different model approaches, such as response tokens, processing speed, and result token efficiency. Using quantitative metrics and qualitative assessments, the research identifies trends and patterns in API performance, highlighting strengths and areas for improvement. The study concludes with recommendations for optimizing API functions, contributing to the broader discourse on advancing AI integration in real-world applications.
AB - Generative AI models have the capability to produce a wide range of new content based on the data they are trained on. These models can generate not just text, but also various types of multimedia content, including images. In recent years, they have become increasingly popular due to their significant impact across multiple fields. They are used in various applications, from text and image generation to music creation, as well as in education, healthcare, robotics, finance, education, autonomous vehicles, and more. However, these models face numerous challenges, such as overfitting the outputs, inconsistency in the results, response time, and token usage. This study presents a comparative analysis of the performance of OpenAI's API, focusing on insights gleaned from AI response statistics. The evaluation encompasses various performance insights on different model approaches, such as response tokens, processing speed, and result token efficiency. Using quantitative metrics and qualitative assessments, the research identifies trends and patterns in API performance, highlighting strengths and areas for improvement. The study concludes with recommendations for optimizing API functions, contributing to the broader discourse on advancing AI integration in real-world applications.
KW - API Response
KW - Generative AI
KW - OpenAI Models
KW - Prompt Engineering
KW - Token
UR - https://www.scopus.com/pages/publications/105012220601
U2 - 10.1109/AIRC64931.2025.11077529
DO - 10.1109/AIRC64931.2025.11077529
M3 - Conference article
AN - SCOPUS:105012220601
SN - 9798331543488
T3 - 2025 6th International Conference on Artificial Intelligence, Robotics and Control (AIRC)
SP - 229
EP - 233
BT - 2025 6th International Conference on Artificial Intelligence, Robotics, and Control, AIRC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 7 May 2025 through 9 May 2025
ER -