Here is how to enable a 1M-token con…

原文与翻译
原文(查看原帖):
Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol.
Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented.
A larger context window lets Codex retain
中文翻译:
【意译】Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. A larger context window lets Codex retain
来源标注:@thsottiaux · 原帖链接
背景
公开资料中,GPT‑6 Astra / GPT‑6.1 Sol / GPT‑6.1 Terra / Ultrafast 等名称出现在 OpenAI DevDay 2026 与随后的产品更新(参见 DevDay 2026 Recap 与开发者 Changelog)。本帖是否对应某一具体正式发布,需以原帖时间线与官方文档为准;未点名的细节不作已核实事实。
意味着什么
Tibo 作为 Codex & ChatGPT 负责人,常在 X 上预告或确认模型侧变化。对订阅用户而言,关键点通常是:是否已在 ChatGPT / Codex / API 可选、用量如何计价、以及是否影响 dots / Work。
我的观点
模型名出现在高管时间线,往往早于或同步于帮助中心更新。中文用户建议同时核对 openai.com 与账户内模型选择器。