Hello GPT-5.3-Codex-Spark! ✨

Our first real-time coding model. It is… FAST. 1,000+ tokens per second.

Once you experience latency this low, it’s hard to go back. This is an exciting first milestone in our partnership with @Cerebras. pic.twitter.com/ieuDkJ1qLz

— Romain Huet (@romainhuet) 12 février 2026

Hello GPT-5.3-Codex-Spark! Our first real-time coding model. It is… FAST. 1,000+ tokens per second. Once you experience latency this low, it’s hard to go back. This is an exciting first milestone in our partnership with @Cerebras
.

→ View original post on X — @romainhuet,