# OpenAI 宣布使用 GPT-5.6 Sol 在 Codex 中优化自身基础设施，实现推理成本降低 20%、token 生成效率提升 15% 以上

- 来源：OpenAI Developers
- 发布时间：2026-07-30 05:33
- AIWatch 分数：65
- AIWatch 标记：当日精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01kyqypymx4c3xzm27nh5ba51p
- 原文链接：https://x.com/OpenAIDevs/status/2082580211552457102

## 精选理由

常规快讯，保留列表

## AI 摘要

OpenAI 宣布使用 GPT-5.6 Sol 在 Codex 中优化自身基础设施，实现推理成本降低 20%、token 生成效率提升 15% 以上。

## 正文

These improvements compound across inference and the agent loop, producing more useful work from the same underlying hardware.

OpenAI: After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run.

The results:
- 20% lower serving costs from production GPU kernel improvements.
- 15%+ better token-generation efficiency from improved speculative decoding.