Documentation 2026-09-27 23:58 UTC to 2026-09-28 22:57 UTC

125On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026.125On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026.

126 126 

127| Shutdown date | Model / system | Recommended replacement |127| Shutdown date | Model / system | Recommended replacement |

128| ------------- | ---------------------- | ----------------------- |128| ------------- | ---------------------- | ------------------------------------------------- |

129| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2` |129| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` |

130| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2` |130| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` |

131| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2` |131| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` |

132 132 

133### Update to OpenAI’s self-serve fine-tuning133### Update to OpenAI’s self-serve fine-tuning

134 134 

147To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below.147To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below.

148 148 

149| Shutdown date | Model snapshot | Substitute model |149| Shutdown date | Model snapshot | Substitute model |

150| ---------------- | ---------------------------------------------------------------------- | ------------------------------------- |150| ---------------- | ---------------------------------------------------------------------- | ------------------------------------------------- |

151| October 23, 2026 | `gpt-3.5-turbo-0125` \| `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.6-terra` |151| October 23, 2026 | `gpt-3.5-turbo-0125` \| `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.6-terra` |

152| October 23, 2026 | `gpt-4-0613` \| `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.6-sol` |152| October 23, 2026 | `gpt-4-0613` \| `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.6-sol` |

153| October 23, 2026 | `gpt-4-1106-preview` | `gpt-5.6-sol` |153| October 23, 2026 | `gpt-4-1106-preview` | `gpt-5.6-sol` |

154| October 23, 2026 | `gpt-4-turbo` \| `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.6-sol` |154| October 23, 2026 | `gpt-4-turbo` \| `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.6-sol` |

155| October 23, 2026 | `gpt-4.1-nano` \| `gpt-4.1-nano-2025-04-14` | `gpt-5.6-luna` |155| October 23, 2026 | `gpt-4.1-nano` \| `gpt-4.1-nano-2025-04-14` | `gpt-5.6-luna` |

156| October 23, 2026 | `gpt-4o-2024-05-13` | `gpt-5.6-sol` |156| October 23, 2026 | `gpt-4o-2024-05-13` | `gpt-5.6-sol` |

157| October 23, 2026 | `gpt-image-1` | `gpt-image-2` |157| October 23, 2026 | `gpt-image-1` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` |

158| October 23, 2026 | `o1-2024-12-17` \| `o1` | `gpt-5.6-sol` |158| October 23, 2026 | `o1-2024-12-17` \| `o1` | `gpt-5.6-sol` |

159| October 23, 2026 | `o1-pro-2025-03-19` \| `o1-pro` | `gpt-5.6-sol` (`reasoning.mode: pro`) |159| October 23, 2026 | `o1-pro-2025-03-19` \| `o1-pro` | `gpt-5.6-sol` (`reasoning.mode: pro`) |

160| October 23, 2026 | `o3-mini-2025-01-31` \| `o3-mini` | `gpt-5.6-sol` |160| October 23, 2026 | `o3-mini-2025-01-31` \| `o3-mini` | `gpt-5.6-sol` |

490 490 

491Choose `none`, `openai_hosted`, or `self_hosted`. [Architecture](https://developers.openai.com/api/docs/guides/agents-api/architecture) explains when to use each option and who manages the environment.491Choose `none`, `openai_hosted`, or `self_hosted`. [Architecture](https://developers.openai.com/api/docs/guides/agents-api/architecture) explains when to use each option and who manages the environment.

492 492 

493For an OpenAI-hosted environment, configure the packages, initial files, and network access the task needs. You can reuse an environment template across sessions. For a self-hosted environment, prepare your compute and [connect an executor](https://developers.openai.com/api/docs/guides/agents-api/environments/self-hosted).493For an OpenAI-hosted environment, [choose a container size](https://developers.openai.com/api/docs/guides/agents-api/environments/openai-hosted#choose-a-container-size) and configure the packages, initial files, and network access the task needs. You can reuse an environment template across sessions. For a self-hosted environment, prepare your compute and [connect an executor](https://developers.openai.com/api/docs/guides/agents-api/environments/self-hosted).

494 494 

495See the [Create session reference](https://developers.openai.com/api/reference/resources/beta/subresources/agents/subresources/sessions/methods/create) for environment fields and [Plugins](https://developers.openai.com/api/docs/guides/agents-api/tools/plugins) for skills, plugins, and templates. See [Session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files) for files you want to keep after execution.495See the [Create session reference](https://developers.openai.com/api/reference/resources/beta/subresources/agents/subresources/sessions/methods/create) for environment fields and [Plugins](https://developers.openai.com/api/docs/guides/agents-api/tools/plugins) for skills, plugins, and templates. See [Session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files) for files you want to keep after execution.

23exit status prevents the agent from starting. Use a setup command to check required23exit status prevents the agent from starting. Use a setup command to check required

24dependencies or files. Templates save configuration, not a running workspace.24dependencies or files. Templates save configuration, not a running workspace.

25 25 

26### Choose a container size

27 

28Set `environment.container_size` when creating a session to choose the CPU and

29memory available to your sandbox. Defaults to `medium`.

30 

31| Size | vCPU | Memory |

32| -------- | ---- | ------ |

33| `small` | 1 | 1 GB |

34| `medium` | 2 | 4 GB |

35| `large` | 4 | 16 GB |

36 

37For example, include this environment in your

38`POST /v1/agents/sessions` request to select `small`:

39 

40```json

41{

42 "environment": {

43 "type": "openai_hosted",

44 "container_size": "small"

45 }

46}

47```

48 

49The returned session reports the selected size in `environment.container_size`.

50This setting applies only to OpenAI-hosted sandboxes.

51 

26### Control network access52### Control network access

27 53 

28| `network.access` | Behavior |54| `network.access` | Behavior |

173<dependency>173<dependency>

174 <groupId>com.openai</groupId>174 <groupId>com.openai</groupId>

175 <artifactId>openai-java</artifactId>175 <artifactId>openai-java</artifactId>

176 <version>4.69.3</version>176 <version>4.70.0</version>

177</dependency>177</dependency>

178```178```

179 179 

190<dependency>190<dependency>

191 <groupId>com.openai</groupId>191 <groupId>com.openai</groupId>

192 <artifactId>openai-java</artifactId>192 <artifactId>openai-java</artifactId>

193 <version>4.69.3</version>193 <version>4.70.0</version>

194</dependency>194</dependency>

195```195```

196 196