Model Details

Domain:

Task:

Model Access:

Hosted access (no API)

AI Tools Usage

This model is commonly used behind the scenes in AI tools.

AI Tools for You

Introduction

Today, we’re releasing a research preview of GPT‑5.3‑Codex‑Spark, a smaller version of GPT‑5.3‑Codex, and our first model designed for real-time coding. Codex-Spark marks the first milestone in our partnership with Cerebras, which we announced in January⁠. Codex-Spark is optimized to feel near-instant when served on ultra-low latency hardware—delivering more than 1000 tokens per second while remaining highly capable for real-world coding tasks.

Training

Training Code AccessibilityRetiring September 2026.

Parameters

Notes: Rumoured by SemiAnalysis (https://newsletter.semianalysis.com/p/cerebras-faster-tokens-please), who may have non-public knowledge, to be of the same size and architecture as GPT-OSS 120B. No public corroboration fo this as of September 2026.

Related ModelsView all models