GPT-5.3-Codex-Spark: OpenAI's Bet on Real-Time AI Coding Hits 1,000 Tokens Per Second

OpenAI’s GPT-5.3-Codex-Spark is a speed-optimized coding model co-developed with Cerebras, delivering over 1,000 tokens per second and a 128k context window for rapid, interactive software development.

GPT-5.3-Codex-Spark: OpenAI's Bet on Real-Time AI Coding Hits 1,000 Tokens Per Second

OpenAI has unveiled GPT-5.3-Codex-Spark, a streamlined coding model optimized for extreme generation speed rather than maximum raw reasoning power. Built in collaboration with Cerebras and deployed on the Wafer-Scale Engine 3 (WSE-3), Spark delivers 1,000+ tokens per second while maintaining strong performance on real-world software engineering benchmarks.