Share

Quoting Thibault Sottiaux

By Simon Willison's Weblog February 21, 2026 · Edited February 21, 2026
We’ve made GPT-5.3-Codex-Spark about 30% faster. It is now serving at over 1200 tokens per second. — Thibault Sottiaux (https://twitter.com/thsottiaux/status/2024947946849186064), OpenAI

We’ve made GPT-5.3-Codex-Spark about 30% faster. It is now serving at over 1200 tokens per second.

— Thibault Sottiaux (https://twitter.com/thsottiaux/status/2024947946849186064), OpenAI

Tags: openai (https://simonwillison.net/tags/openai), llms (https://simonwillison.net/tags/llms), ai (https://simonwillison.net/tags/ai), generative-ai (https://simonwillison.net/tags/generative-ai)
Write a comment
No comments yet.