Simon Willison • 2/12/2026

Introducing GPT‑5.3‑Codex‑Spark

Read Original

OpenAI, in partnership with Cerebras, announces GPT-5.3-Codex-Spark, a smaller, faster version of GPT-5.3-Codex designed for real-time coding. The model features a 128k context window, is text-only, and claims speeds of up to 1,000 tokens/second, enabling developers to maintain flow state during iterative coding sessions. The article details performance comparisons and potential use cases, though pricing remains unconfirmed.

0 comments
#ai coding #code generation #Openai
Introducing GPT‑5.3‑Codex‑Spark

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
Quoting Thariq Shihipar
Simon Willison • 2 votes
2
Container queries are rad AF!
Chris Ferdinandi • 1 votes
3
Top picks — 2026 January
Paweł Grzybek • 1 votes
4
In Praise of –dry-run
Henrik Warne • 1 votes
5
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
Ferenc Huszár • 1 votes
6
Vibe coding your first iOS app
William Denniss • 1 votes
7
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes