SpyBara
Go Premium

Documentation 2026-08-10 19:00 UTC to 2026-08-11 19:59 UTC

3 files changed +13 −12. View all changes and history on the product overview
2026
Wed 12 02:57 Tue 11 19:59 Mon 10 19:00 Fri 7 00:58 Thu 6 21:58 Wed 5 18:01 Tue 4 22:59 Mon 3 18:01

deprecations.md +9 −9

Details

109| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2` |109| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2` |

110| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2` |110| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2` |

111 111 

112### 2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots

113 

114On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API.

115 

116| Shutdown date | Model / system | Recommended replacement |

117| ------------- | --------------------- | ----------------------- |

118| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` |

119| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` |

120 

121### Update to OpenAI’s self-serve fine-tuning112### Update to OpenAI’s self-serve fine-tuning

122 113 

123On May 7th, 2026, we notified developers using OpenAI’s self-serve fine-tuning platform of updates to availability.114On May 7th, 2026, we notified developers using OpenAI’s self-serve fine-tuning platform of updates to availability.


199 190 

200Past deprecations are listed below, with the most recent announcements at the top.191Past deprecations are listed below, with the most recent announcements at the top.

201 192 

193### 2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots

194 

195On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API.

196 

197| Shutdown date | Model / system | Recommended replacement |

198| ------------- | --------------------- | ----------------------- |

199| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` |

200| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` |

201 

202### 2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)202### 2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)

203 203 

204On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026.204On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026.

Details

243[Codex Auto-review](https://developers.openai.com/codex/sandboxing/auto-review). Add review and enforcement243[Codex Auto-review](https://developers.openai.com/codex/sandboxing/auto-review). Add review and enforcement

244to your own harness. The244to your own harness. The

245[open-source Codex reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)245[open-source Codex reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)

246illustrates one approach; [Cyber Safety](https://developers.openai.com/codex/cyber-safety) explains approved246illustrates one approach. Review [Models and Trusted Access](https://developers.openai.com/codex/cyber-safety)

247model access and safe engagement setup.247for approved model access and [Recommended configuration](https://developers.openai.com/codex/cyber-safety/recommended-configuration)

248for safe engagement setup.

248 249 

249## Streaming and delayed review use the same state model250## Streaming and delayed review use the same state model

250 251 

Details

188Learn more:188Learn more:

189 189 

190- [Model evaluations hub](https://openai.com/safety/evaluations-hub)190- [Model evaluations hub](https://openai.com/safety/evaluations-hub)

191- [Cyber Safety](https://developers.openai.com/codex/cyber-safety)191- [Cyber safety models](https://developers.openai.com/codex/cyber-safety)

192- [Fine-tuning safety](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#safety-checks)192- [Fine-tuning safety](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#safety-checks)

193- [Safety checks in computer use](https://developers.openai.com/api/docs/guides/tools-computer-use#handle-user-confirmation-and-consent)193- [Safety checks in computer use](https://developers.openai.com/api/docs/guides/tools-computer-use#handle-user-confirmation-and-consent)