Documentation 2026-06-02 06:51 UTC to 2026-06-03 06:53 UTC

6 6 

7This page lists all API deprecations, along with recommended replacements.7This page lists all API deprecations, along with recommended replacements.

8 8 

9## Model deprecation notice periods

10 

11We provide advance notice before retiring models so customers have time to plan and migrate. When we announce a model deprecation, we notify customers who are actively using the model by email and document the deprecation on this page.

12 

13Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement:

14 

15- **Generally available models:** At least 6 months.

16- **Specialized variants of generally available models:** At least 3 months. Examples include chat variants such as `gpt-5.1-chat-latest`, Codex variants such as `gpt-5.3-codex`, and deep research variants such as `o3-deep-research`.

17- **Preview models:** Preview models, identified by `preview` in the model name, may be retired with much shorter notice, such as 2 weeks. Examples include `computer-use-preview` and `gpt-4o-audio-preview`. We don't recommend using preview models for business-critical production workloads unless you can migrate on short notice.

18 

19If safety or compliance concerns require us to retire a model sooner, we will provide as much notice as reasonably possible.

20 

21These notice periods give customers time to evaluate recommended replacement models, test application behavior, and complete migrations before a model is no longer available. In some cases, developers may be able to provision dedicated capacity for continued access after a model's shutdown date. To explore this option, [contact our sales team](https://openai.com/contact-sales/).

22 

9## Deprecation vs. legacy23## Deprecation vs. legacy

10 24 

11We use the term "deprecation" to refer to the process of retiring a model or endpoint. When we announce that a model or endpoint is being deprecated, it immediately becomes deprecated. All deprecated models and endpoints will also have a shut down date. At the time of the shut down, the model or endpoint will no longer be accessible.25We use the term "deprecation" to refer to the process of retiring a model or endpoint. When we announce that a model or endpoint is being deprecated, it immediately becomes deprecated. All deprecated models and endpoints will also have a shut down date. At the time of the shut down, the model or endpoint will no longer be accessible.

18 32 

19Upcoming deprecations are listed below, with the most recent announcements at the top.33Upcoming deprecations are listed below, with the most recent announcements at the top.

20 34 

35### 2026-06-02: GPT Image model deprecations

36 

37On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026.

38 

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

40| ------------- | ---------------------- | ----------------------- |

41| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2` |

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

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

44 

21### 2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots45### 2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots

22 46 

23On 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.47On 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.

123 123 

124All tools are loaded at the end of the model's context window. This holds true for both hosted tool search and client-executed tool search. This allows the model's cache to be preserved from one request to another, lowering overall costs and boosting speed.124All tools are loaded at the end of the model's context window. This holds true for both hosted tool search and client-executed tool search. This allows the model's cache to be preserved from one request to another, lowering overall costs and boosting speed.

125 125 

126### Add tools at a specific point in the input

127 

128For advanced workflows, you can use an `additional_tools` input item to make tools available at a specific point in the conversation. This is useful when your application loads tools outside the normal tool search flow or needs to preserve the ordering of tools added during a previous response.

129 

130Set `role` to `developer` and include the tools to add in the item's `tools` array:

131 

132```json

133{

134 "type": "additional_tools",

135 "role": "developer",

136 "tools": [

137 {

138 "type": "function",

139 "name": "get_customer",

140 "description": "Look up a customer by ID.",

141 "parameters": {

142 "type": "object",

143 "properties": {

144 "customer_id": { "type": "string" }

145 },

146 "required": ["customer_id"],

147 "additionalProperties": false

148 }

149 }

150 ]

151 }

152```

153 

154 

155Tools in an `additional_tools` item become available only after that item appears in the input. When you manually round-trip conversation items, preserve the item's position so the model sees the same tools at the same point in the conversation.

156 

126## Related guides157## Related guides

127 158 

128- Use [function calling](https://developers.openai.com/api/docs/guides/function-calling) to define callable functions and custom tools.159- Use [function calling](https://developers.openai.com/api/docs/guides/function-calling) to define callable functions and custom tools.