Jason Liu (OpenAI) answers your most asked questions about Codex Spark | Cerebras

Jason Liu from OpenAI's Developer Experience team answers your most asked questions about GPT-5.3-Codex-Spark, powered by Cerebras. Codex Spark is a lighter, faster version of Codex running on Cerebras' specialized AI chips — built for speed, interactivity, and real-time coding workflows. In this video, Jason breaks down how it works, when to use it, and how OpenAI engineers are using Codex internally. 00:25 – What is Cerebras and why does it make Spark faster? 00:41 – When should I use Codex vs. Codex Spark? 01:35 – How many Codex sessions do you run at once? 02:04 – What do OpenAI engineers use Codex for? 02:32 – What makes Codex slower? The best workflows blend both models. Codex handles complex planning and sophisticated features. Spark handles research, function calls, and real-time interactive coding. Together, they give developers a complete toolkit. Learn more about Codex Spark and try it inside the Codex app today: https://openai.com/index/introducing-gpt-5-3-codex-spark/ +++ Subscribe to our channel! https://www.youtube.com/@Cerebras Cerebras builds the world’s largest AI chip — delivering up to 20× faster inference than leading GPUs. Our mission is to engineer the future of compute and make state-of-the-art AI accessible to every team. Explore our newest open-source models and get free compute at http://cerebras.ai/ . Watch our full video library: https://youtube.com/@Cerebras/videos Read the latest engineering deep dives on our blog: https://cerebras.ai/blog Explore our systems and technology: https://cerebras.ai/publications Follow Cerebras on X: https://x.com/cerebras Connect with us on LinkedIn: https://linkedin.com/company/cerebras-systems