OpenAI releases the GPT-5.3-Codex-Spark research preview

OpenAI today released the GPT-5.3-Codex-Spark research preview, a streamlined version of GPT-5.3-Codex, and the first model designed specifically for real-time coding, supporting targeted editing, reshaping logic, or optimizing interfaces, with immediate result visibility.

Codex-Spark has been optimized to run on ultra-low latency hardware, achieving near-instantaneous responses—delivering over 1000 tokens per second while still handling actual coding tasks.