4 4 

5## Overview5## Overview

6 6 

7As we launch safer and more capable models, we regularly retire older models. Software relying on OpenAI models may need occasional updates to keep working. Impacted customers will always be notified by email and in our documentation along with [blog posts](https://openai.com/blog) for larger changes.7As we launch safer and more capable models, we regularly retire older models. Software relying on OpenAI models may need occasional updates to keep working. Impacted customers will always be notified by email and in our documentation.

8 8 

9This page lists all API deprecations, along with recommended replacements.9Each model has one of three lifecycle states.

10 10 

11To monitor model shutdowns programmatically, call the [List models endpoint](https://developers.openai.com/api/reference/resources/models/methods/list) (`GET /v1/models`) and check each model's optional `shutdown_date` field. When present, this field contains the shutdown date as a `YYYY-MM-DD` string, or `null` if no shutdown date has been announced; the field is also available from the [Retrieve a model endpoint](https://developers.openai.com/api/reference/resources/models/methods/retrieve).11- **Active.** You can use the model through the API. OpenAI hasn't announced its retirement.

12- **Deprecated.** OpenAI has announced the model's retirement. You can still use it until its shutdown date.

13- **Shutdown.** The model no longer accepts requests through the standard API.

12 14 

13## Model deprecation notice periods15For deprecation notice periods and help migrating to a replacement model, see the [deprecation policy](#model-deprecation-notice-periods) and [migration guidance](#migration-guidance) below.

14 

15We 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.

16 

17Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement:

18 16 

19- **Generally available models:** At least 6 months.17See [feature and endpoint deprecations](#feature-and-endpoint-deprecations) for other upcoming API shutdowns.

20- **Specialized variants of generally available models and image generation 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`.

21- **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.

22 

23If safety or compliance concerns require us to retire a model sooner, we will provide as much notice as reasonably possible.

24 

25These 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/).

26 

27## Deprecation vs. legacy

28 

29We 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.

30 

31We use the terms "sunset" and "shut down" interchangeably to mean a model or endpoint is no longer accessible.

32 

33We use the term "legacy" to refer to models and endpoints that no longer receive updates. We tag endpoints and models as legacy to signal to developers where we're moving as a platform and that they should likely migrate to newer models or endpoints. You can expect that a legacy model or endpoint will be deprecated at some point in the future.

34 18 

35## Upcoming deprecations19## Upcoming deprecations

36 20 

37Upcoming deprecations are listed below, with the most recent announcements at the top.

38 

39### 2026-11-10: GPT Image 2

40 21 

41The `gpt-image-2` model and `gpt-image-2-2026-04-21` snapshot are deprecated and will be removed from the API on February 10, 2027.

42 22 

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

44| ----------------- | ----------------------------------------- | ------------------------------------------------- |

45| February 10, 2027 | `gpt-image-2` \| `gpt-image-2-2026-04-21` | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` |

46 23 

47### 2026-11-05: GPT-5.5-Cyber24| Shutdown date | Affected model | Status | Recommended replacement | Notice date |

25| ---------------- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ | ---------------------------------------------------------- | ------------ |

26| **Dec 1, 2026** | `gpt-image-1-mini` | Deprecated | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` | Jun 2, 2026 |

27| **Dec 1, 2026** | `gpt-image-1.5`, `gpt-image-1.5-2025-12-16` | Deprecated | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` | Jun 2, 2026 |

28| **Dec 1, 2026** | `chatgpt-image-latest` | Deprecated | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` | Jun 2, 2026 |

29| **Dec 11, 2026** | `gpt-5`, `gpt-5-2025-08-07` | Deprecated | `gpt-6.1-sol` | Jun 11, 2026 |

30| **Dec 11, 2026** | `gpt-5-mini`, `gpt-5-mini-2025-08-07` | Deprecated | `gpt-6.1-terra` | Jun 11, 2026 |

31| **Dec 11, 2026** | `gpt-5-nano`, `gpt-5-nano-2025-08-07` | Deprecated | `gpt-6-luna` | Jun 11, 2026 |

32| **Dec 11, 2026** | `gpt-5-pro`, `gpt-5-pro-2025-10-06` | Deprecated | `gpt-6.1-sol` (`reasoning.mode: pro`) in the Responses API | Jun 11, 2026 |

33| **Dec 11, 2026** | `o3`, `o3-2025-04-16` | Deprecated | `gpt-6.1-sol` | Jun 11, 2026 |

34| **Dec 11, 2026** | `o3-pro`, `o3-pro-2025-06-10` | Deprecated | `gpt-6.1-sol` (`reasoning.mode: pro`) in the Responses API | Jun 11, 2026 |

35| **Jan 6, 2027** | `tts-1` | Deprecated | `gpt-realtime-2.1-mini` | Oct 1, 2026 |

36| **Jan 6, 2027** | `tts-1-hd` | Deprecated | `gpt-realtime-2.1-mini` | Oct 1, 2026 |

37| **Jan 6, 2027** | `gpt-4o-mini-tts`, `gpt-4o-mini-tts-2025-03-20`, `gpt-4o-mini-tts-2025-12-15` | Deprecated | `gpt-realtime-2.1-mini` | Oct 1, 2026 |

38| **Jan 14, 2027** | GPT-4o (`gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`) | Deprecated | `gpt-6-luna` | Oct 14, 2026 |

39| **Jan 14, 2027** | GPT-4o mini (`gpt-4o-mini-2024-07-18`) | Deprecated | `gpt-6-luna` | Oct 14, 2026 |

40| **Jan 14, 2027** | GPT-4.1 (`gpt-4.1-2025-04-14`) | Deprecated | `gpt-6-luna` | Oct 14, 2026 |

41| **Jan 14, 2027** | GPT-4.1 mini (`gpt-4.1-mini-2025-04-14`) | Deprecated | `gpt-6-luna` | Oct 14, 2026 |

42| **Jan 20, 2027** | `gpt-realtime`, `gpt-realtime-2025-08-28` | Deprecated | `gpt-realtime-2.1` | Jul 20, 2026 |

43| **Jan 20, 2027** | `gpt-audio`, `gpt-audio-2025-08-28` | Deprecated | `gpt-audio-1.5` | Jul 20, 2026 |

44| **Jan 20, 2027** | `gpt-4o-audio` | Deprecated | `gpt-audio-1.5` | Jul 20, 2026 |

45| **Jan 20, 2027** | `gpt-4o-realtime` | Deprecated | `gpt-realtime-2.1` | Jul 20, 2026 |

46| **Jan 20, 2027** | `gpt-realtime-mini`, `gpt-realtime-mini-2025-12-15` | Deprecated | `gpt-realtime-2.1-mini` | Jul 20, 2026 |

47| **Jan 20, 2027** | `gpt-audio-mini`, `gpt-audio-mini-2025-12-15` | Deprecated | `gpt-audio-1.5` | Jul 20, 2026 |

48| **Jan 20, 2027** | `gpt-4o-mini-realtime` | Deprecated | `gpt-realtime-2.1-mini` | Jul 20, 2026 |

49| **Jan 20, 2027** | `gpt-4o-mini-audio` | Deprecated | `gpt-audio-1.5` | Jul 20, 2026 |

50| **Jan 20, 2027** | `gpt-4o-mini-transcribe-2025-03-20` | Deprecated | `gpt-4o-mini-transcribe-2025-12-15` | Jul 20, 2026 |

51| **Feb 1, 2027** | `gpt-5.5-cyber-preview` | Deprecated | The most capable cyber model available to you. | Nov 5, 2026 |

52| **Feb 10, 2027** | `gpt-image-2`, `gpt-image-2-2026-04-21` | Deprecated | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` | Nov 10, 2026 |

53| **Feb 26, 2027** | `whisper-1` | Deprecated | `gpt-live-transcribe` or `gpt-transcribe` | Aug 26, 2026 |

54| **Feb 26, 2027** | `gpt-4o-transcribe` | Deprecated | `gpt-live-transcribe` or `gpt-transcribe` | Aug 26, 2026 |

55| **Feb 26, 2027** | `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15` | Deprecated | `gpt-live-transcribe` or `gpt-transcribe` | Aug 26, 2026 |

56| **Feb 26, 2027** | `gpt-4o-transcribe-diarize` | Deprecated | `gpt-live-transcribe` or `gpt-transcribe` | Aug 26, 2026 |

57| **Apr 1, 2027** | `gpt-5.3-codex` | Deprecated | `gpt-6-sol` | Oct 1, 2026 |

58| **Apr 1, 2027** | `gpt-5.4-nano`, `gpt-5.4-nano-2026-03-17` | Deprecated | `gpt-6-luna` | Oct 1, 2026 |

59| **Apr 1, 2027** | `gpt-5.1`, `gpt-5.1-2025-11-13` | Deprecated | `gpt-6-sol` | Oct 1, 2026 |

48 60 

49The `gpt-5.5-cyber-preview` model is deprecated and will be removed from the API on February 1, 2027. Migrate to the most capable cyber model available to you before the shutdown date.

50 61 

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

52| ---------------- | ----------------------- | ---------------------------------------------- |

53| February 1, 2027 | `gpt-5.5-cyber-preview` | The most capable cyber model available to you. |

54 62 

55### 2026-10-14: GPT-4 series model deprecations

56 63 

57On October 14, 2026, we notified developers using certain GPT-4 series models of their deprecation and removal from the API on January 14, 2027.64Fine-tuned versions of the models listed above follow the same shutdown schedule as their underlying base models.

58 65 

59| Shutdown date | Model / system | Recommended replacement |66For speech migrations, see the [Realtime API guide](https://developers.openai.com/api/docs/guides/realtime) and the [transcription guide](https://developers.openai.com/api/docs/guides/transcription).

60| ---------------- | ------------------------------------------------- | ----------------------- |

61| January 14, 2027 | GPT-4o (`gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`) | `gpt-6-luna` |

62| January 14, 2027 | GPT-4o mini (`gpt-4o-mini-2024-07-18`) | `gpt-6-luna` |

63| January 14, 2027 | GPT-4.1 (`gpt-4.1-2025-04-14`) | `gpt-6-luna` |

64| January 14, 2027 | GPT-4.1 mini (`gpt-4.1-mini-2025-04-14`) | `gpt-6-luna` |

65 67 

66Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models.68## Feature and endpoint deprecations

67 69 

68### 2026-10-01: GPT-5.3-Codex, GPT-5.1, GPT-5.4 nano

69 70 

70The following models are deprecated and will be removed from the API on April 1, 2027, with six months' notice. Migrate to the recommended replacements before the shutdown date.

71 71 

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

73| ------------- | ------------------------------------------- | ----------------------- |

74| Apr 1, 2027 | `gpt-5.3-codex` | `gpt-6-sol` |

75| Apr 1, 2027 | `gpt-5.4-nano` \| `gpt-5.4-nano-2026-03-17` | `gpt-6-luna` |

76| Apr 1, 2027 | `gpt-5.1` \| `gpt-5.1-2025-11-13` | `gpt-6-sol` |

77 72 

78### 2026-10-01: Text-to-speech models73| Shutdown date | Affected feature or endpoint | Status | Recommended replacement | Notice date |

74| ---------------- | ------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------ |

75| **Nov 30, 2026** | `/v1/prompts` and reusable prompt objects | Deprecated | Move prompt content into your application code. [Migration guide](https://developers.openai.com/api/docs/guides/prompting/migrate-from-prompt-object) | Jun 3, 2026 |

76| **Nov 30, 2026** | Evals dashboard, API, and graders for eval workflows | Read-only | [Migrate to Promptfoo](https://developers.openai.com/cookbook/examples/evaluation/moving-from-openai-evals-to-promptfoo). For fine-tuning graders, see the [fine-tuning timeline](#update-to-openais-self-serve-fine-tuning). | Jun 3, 2026 |

77| **Nov 30, 2026** | Agent Builder | Deprecated | Agents SDK or ChatGPT Workspace Agents. [Migration guide](https://developers.openai.com/api/docs/guides/agent-builder/migrate-from-agent-builder). ChatKit remains available. | Jun 3, 2026 |

78| **Jan 6, 2027** | Self-serve fine-tuning job creation | Restricted access | See the [fine-tuning timeline](#update-to-openais-self-serve-fine-tuning). | May 7, 2026 |

79| **Feb 26, 2027** | `/v1/audio/translations` | Deprecated | [`/v1/realtime/translations`](https://developers.openai.com/api/docs/guides/realtime-translation) | Aug 26, 2026 |

79 80 

80The following text-to-speech models are deprecated and will be removed from the API on January 6, 2027, with at least three months' notice. Migrate to `gpt-realtime-2.1-mini` before the shutdown date. See the [Realtime API guide](https://developers.openai.com/api/docs/guides/realtime) to plan your migration.

81 81 

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

83| ------------- | ------------------------------------------------- | ----------------------- |

84| Jan 6, 2027 | `tts-1` | `gpt-realtime-2.1-mini` |

85| Jan 6, 2027 | `tts-1-hd` | `gpt-realtime-2.1-mini` |

86| Jan 6, 2027 | `gpt-4o-mini-tts` \| `gpt-4o-mini-tts-2025-03-20` | `gpt-realtime-2.1-mini` |

87| Jan 6, 2027 | `gpt-4o-mini-tts` \| `gpt-4o-mini-tts-2025-12-15` | `gpt-realtime-2.1-mini` |

88 

89### 2026-08-26: Transcription models

90 

91On August 26, 2026, we notified developers using `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-transcribe-diarize` of their deprecation and removal from the API on February 26, 2027.

92 

93For information about the recommended replacements, see the [transcription guide](https://developers.openai.com/api/docs/guides/transcription).

94 

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

96| ------------- | --------------------------------------------------------------- | ----------------------------------------- |

97| Feb 26, 2027 | `whisper-1` | `gpt-live-transcribe` or `gpt-transcribe` |

98| Feb 26, 2027 | `gpt-4o-transcribe` | `gpt-live-transcribe` or `gpt-transcribe` |

99| Feb 26, 2027 | `gpt-4o-mini-transcribe` \| `gpt-4o-mini-transcribe-2025-12-15` | `gpt-live-transcribe` or `gpt-transcribe` |

100| Feb 26, 2027 | `gpt-4o-transcribe-diarize` | `gpt-live-transcribe` or `gpt-transcribe` |

101| Feb 26, 2027 | `/v1/audio/translations` | `v1/realtime/translations` |

102 

103### 2026-07-20: Legacy audio, realtime, and transcription models

104 

105On July 20, 2026, we notified developers using legacy audio, realtime, and transcription model families and snapshots of their deprecation and removal from the API on January 20, 2027.

106 

107| Shutdown date | Model family / snapshot | Recommended replacement |

108| ------------- | ----------------------------------------------------- | ----------------------------------- |

109| Jan 20, 2027 | `gpt-realtime` \| `gpt-realtime-2025-08-28` | `gpt-realtime-2.1` |

110| Jan 20, 2027 | `gpt-audio` \| `gpt-audio-2025-08-28` | `gpt-audio-1.5` |

111| Jan 20, 2027 | `gpt-4o-audio` | `gpt-audio-1.5` |

112| Jan 20, 2027 | `gpt-4o-realtime` | `gpt-realtime-2.1` |

113| Jan 20, 2027 | `gpt-realtime-mini` \| `gpt-realtime-mini-2025-12-15` | `gpt-realtime-2.1-mini` |

114| Jan 20, 2027 | `gpt-audio-mini` \| `gpt-audio-mini-2025-12-15` | `gpt-audio-1.5` |

115| Jan 20, 2027 | `gpt-4o-mini-realtime` | `gpt-realtime-2.1-mini` |

116| Jan 20, 2027 | `gpt-4o-mini-audio` | `gpt-audio-1.5` |

117| Jan 20, 2027 | `gpt-4o-mini-transcribe-2025-03-20` | `gpt-4o-mini-transcribe-2025-12-15` |

118 

119### 2026-06-11: GPT-5 and o3 model deprecations

120 

121On June 11, 2026, we notified developers using older GPT-5 and o3 model snapshots of their deprecation and removal from the API on December 11, 2026.

122 

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

124| ------------- | --------------------------------------- | ------------------------------------- |

125| Dec 11, 2026 | `gpt-5` \| `gpt-5-2025-08-07` | `gpt-5.6-sol` |

126| Dec 11, 2026 | `gpt-5-mini` \| `gpt-5-mini-2025-08-07` | `gpt-5.6-terra` |

127| Dec 11, 2026 | `gpt-5-nano` \| `gpt-5-nano-2025-08-07` | `gpt-5.6-luna` |

128| Dec 11, 2026 | `gpt-5-pro` \| `gpt-5-pro-2025-10-06` | `gpt-5.6-sol` (`reasoning.mode: pro`) |

129| Dec 11, 2026 | `o3` \| `o3-2025-04-16` | `gpt-5.6-sol` |

130| Dec 11, 2026 | `o3-pro` \| `o3-pro-2025-06-10` | `gpt-5.6-sol` (`reasoning.mode: pro`) |

131 

132Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models.

133 

134### 2026-06-03: Reusable prompts

135 

136On June 3, 2026, we notified developers using reusable prompts in the dashboard and API that reusable prompt objects are being deprecated.

137 

138| Date | Update |

139| ------------ | ---------------------------------------------------------------------------- |

140| June 3, 2026 | Deprecation announced and prompt creation de-emphasized in the platform. |

141| Nov 30, 2026 | The `v1/prompts` API and reusable prompt objects are scheduled to shut down. |

142 82 

143To migrate, move reusable prompt content into your application code. See [Migrate from prompt objects](https://developers.openai.com/api/docs/guides/prompting/migrate-from-prompt-object).

144 83 

145### 2026-06-03: Evals platform84## Model deprecation notice periods

146 

147On June 3, 2026, we notified developers using the Evals platform that the product is being deprecated.

148 

149| Date | Update |

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

151| June 3, 2026 | Deprecation announced for the Evals platform. |

152| Oct 31, 2026 | Existing evals become read-only. |

153| Nov 30, 2026 | The Evals dashboard and API are scheduled to shut down. |

154 

155Graders documented for eval workflows are part of this transition. Fine-tuning-related timelines remain covered in the self-serve fine-tuning section below.

156 85 

157See [Moving from OpenAI Evals to Promptfoo](https://developers.openai.com/cookbook/examples/evaluation/moving-from-openai-evals-to-promptfoo) for a migration path.86We 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.

158 87 

159### 2026-06-03: Agent Builder88Unless safety or compliance concerns require a faster timeline, we provide the following minimum notice periods before model retirement:

160 89 

161On June 3, 2026, we notified developers using Agent Builder that the product is being deprecated. ChatKit remains available.90- **Generally available models:** At least 6 months.

91- **Specialized variants of generally available models and image generation 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`.

92- **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.

162 93 

163| Date | Update |94These 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/).

164| ------------ | ---------------------------------------- |

165| June 3, 2026 | Deprecation announced for Agent Builder. |

166| Nov 30, 2026 | Agent Builder is scheduled to shut down. |

167 95 

168See [Migrate from Agent Builder](https://developers.openai.com/api/docs/guides/agent-builder/migrate-from-agent-builder) to continue with the Agents SDK or ChatGPT Workspace Agents.96## Best practices

169 97 

170### 2026-06-02: GPT Image model deprecations98- Check **the documentation** regularly for model deprecation updates.

99- To monitor model shutdowns **programmatically**, call the [List models endpoint](https://developers.openai.com/api/reference/resources/models/methods/list) (`GET /v1/models`) and check each model's optional `shutdown_date` field. The field is also available from the [Retrieve a model endpoint](https://developers.openai.com/api/reference/resources/models/methods/retrieve).

171 100 

172On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026.101## Migration guidance

173 102 

174| Shutdown date | Model / system | Recommended replacement |103- In Codex, invoke the [OpenAI Docs skill](https://github.com/openai/codex/tree/main/codex-rs/skills/src/assets/samples/openai-docs) with `$openai-docs` and ask it to migrate your project to the recommended replacement.

175| ------------- | --------------------------------------------- | ------------------------------------------------- |104- See the [**GPT-6 migration guide**](https://developers.openai.com/api/docs/guides/latest-model#gpt-6-astra-migration-quickstart).

176| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` |105- Run representative requests against both models. Compare outputs, latency, and cost before switching production traffic to the replacement.

177| Dec 1, 2026 | `gpt-image-1.5` \| `gpt-image-1.5-2025-12-16` | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` |

178| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2.6-sunburst` or `gpt-image-2.6-flare` |

179 106 

180### Update to OpenAI’s self-serve fine-tuning107## Update to OpenAI’s self-serve fine-tuning

181 108 

182On May 7th, 2026, we notified developers using OpenAI’s self-serve fine-tuning platform of updates to availability.109On May 7th, 2026, we notified developers using OpenAI’s self-serve fine-tuning platform of updates to availability.

183 110 

189| July 2, 2026 | Creating fine-tuning jobs is no longer available to organizations that have not run inference on a fine-tuned model in the past 60 days. |116| July 2, 2026 | Creating fine-tuning jobs is no longer available to organizations that have not run inference on a fine-tuned model in the past 60 days. |

190| Jan 6, 2027 | Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated. |117| Jan 6, 2027 | Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated. |

191 118 

192## Past deprecations

193 

194Past deprecations are listed below, with the most recent announcements at the top.

195 

196### 2026-09-11: GPT-5.4-Cyber

197 

198The `gpt-5.4-cyber` model is deprecated and will be removed from the API on October 1, 2026. Migrate to the most capable cyber model available to you before the shutdown date.

199 

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

201| ------------- | --------------- | ---------------------------------------------- |

202| Oct 1, 2026 | `gpt-5.4-cyber` | The most capable cyber model available to you. |

203 

204### 2026-05-08: `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots

205 

206On 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.

207 

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

209| ------------- | --------------------- | ----------------------- |

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

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

212 

213### 2026-04-22: Legacy GPT model snapshots

214 

215On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on October 23, 2026.

216 

217| Shutdown date | Model snapshot | Substitute model |

218| ---------------- | ---------------------------------------------------------------------- | ------------------------------------------------- |

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

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

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

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

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

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

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

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

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

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

229| October 23, 2026 | `ft-o4-mini-2025-04-16` | `gpt-5.6-terra` |

230| October 23, 2026 | `o4-mini-2025-04-16` \| `o4-mini` | `gpt-5.6-terra` |

231 

232Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models.

233 

234### 2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)

235 

236On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026.

237 

238| Shutdown date | Model snapshot | Substitute model |

239| ------------- | ------------------------------------------------------------- | ----------------------- |

240| July 23, 2026 | `computer-use-preview-2025-03-11` \| `computer-use-preview` | `gpt-5.6-terra` |

241| July 23, 2026 | `gpt-4o-mini-search-preview-2025-03-11` | `gpt-5.6-terra` |

242| July 23, 2026 | `gpt-4o-search-preview-2025-03-11` | `gpt-5.6-terra` |

243| July 23, 2026 | `gpt-5-chat-latest` | `gpt-5.6-sol` |

244| July 23, 2026 | `gpt-5-codex` | `gpt-5.6-sol` |

245| July 23, 2026 | `gpt-5.1-chat-latest` | `gpt-5.6-sol` |

246| July 23, 2026 | `gpt-5.1-codex` | `gpt-5.6-sol` |

247| July 23, 2026 | `gpt-5.1-codex-max` | `gpt-5.6-sol` |

248| July 23, 2026 | `gpt-5.1-codex-mini` | `gpt-5.6-terra` |

249| July 23, 2026 | `gpt-audio-mini-2025-10-06` | `gpt-audio-1.5` |

250| July 23, 2026 | `gpt-realtime-mini-2025-10-06` | `gpt-realtime-2.1-mini` |

251| July 23, 2026 | `o3-deep-research-2025-06-26` \| `o3-deep-research` | `gpt-5.6-sol` |

252| July 23, 2026 | `o4-mini-deep-research-2025-06-26` \| `o4-mini-deep-research` | `gpt-5.6-sol` |

253| July 23, 2026 | `gpt-5.2-codex` | `gpt-5.6-sol` |

254 

255### 2026-03-24: Sora 2 video generation models and Videos API

256 

257On March 24th, 2026, we notified developers using the Videos API and Sora 2 video generation model aliases and snapshots of their deprecation and removal from the API on September 24, 2026.

258 

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

260| ------------- | ----------------------- | ----------------------- |

261| 2026-09-24 | Videos API | --- |

262| 2026-09-24 | `sora-2` | --- |

263| 2026-09-24 | `sora-2-pro` | --- |

264| 2026-09-24 | `sora-2-2025-10-06` | --- |

265| 2026-09-24 | `sora-2-2025-12-08` | --- |

266| 2026-09-24 | `sora-2-pro-2025-10-06` | --- |

267 119 

268### 2025-11-18: `chatgpt-4o-latest` snapshot

269 120 

270On November 18th, 2025, we notified developers using `chatgpt-4o-latest` model snapshot of its deprecation and removal from the API on February 17, 2026.121<a id="past-deprecations"></a>

271 122 

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

273| ------------- | ------------------- | ----------------------- |

274| 2026-02-17 | `chatgpt-4o-latest` | `gpt-5.1-chat-latest` |

275 123 

276### 2025-11-17: `codex-mini-latest` model snapshot

277 124 

278On November 17th, 2025, we notified developers using `codex-mini-latest` model of its deprecation and removal from the API on February 12, 2026. As part of this deprecation, we will no longer support our legacy local shell tool, which is only available for use with `codex-mini-latest`. For new use cases, please use our latest shell tool.125## Past deprecations

279 

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

281| ------------- | ------------------- | ----------------------- |

282| 2026-02-12 | `codex-mini-latest` | `gpt-5-codex-mini` |

283 

284### 2025-11-14: DALL·E model snapshots

285 

286On November 14th, 2025, we notified developers using DALL·E model snapshots of their deprecation and removal from the API on May 12, 2026.

287 

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

289| ------------- | -------------- | --------------------------------------------------- |

290| 2026-05-12 | `dall-e-2` | `gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini` |

291| 2026-05-12 | `dall-e-3` | `gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini` |

292 

293### 2025-09-26: Legacy GPT model snapshots

294 

295To improve reliability and make it easier for developers to choose the right models, we deprecated a set of older OpenAI models with declining usage. Access to these models was shut down on September 28, 2026.

296 

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

298| ------------- | ------------------------ | ----------------------- |

299| 2026-09-28 | `gpt-3.5-turbo-instruct` | `gpt-5.6-terra` |

300| 2026-09-28 | `babbage-002` | `gpt-5.6-terra` |

301| 2026-09-28 | `davinci-002` | `gpt-5.6-terra` |

302| 2026-09-28 | `gpt-3.5-turbo-1106` | `gpt-5.6-terra` |

303 

304### 2025-09-26: Legacy GPT model snapshots (March 2026 shutdown)

305 

306To improve reliability and make it easier for developers to choose the right models, we deprecated a set of older OpenAI models with declining usage. Access to these models was shut down on March 26, 2026.

307 

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

309| ------------- | -------------------------------------------------------------------------------------------------------------------------- | ----------------------- |

310| 2026‑03‑26 | `gpt-4-0314` | `gpt-5` or `gpt-4.1*` |

311| 2026‑03‑26 | `gpt-4-0125-preview` (including `gpt-4-turbo-preview` and `gpt-4-turbo-preview-completions`, which point to this snapshot) | `gpt-5` or `gpt-4.1*` |

312 

313\*For tasks that are especially latency sensitive and don't require reasoning

314 

315### 2025-09-15: Realtime API Beta

316 

317The Realtime API Beta was deprecated and removed from the API on May 12, 2026.

318 

319The interfaces in the Realtime beta API and the released GA API have a few key differences. See [the migration guide](https://developers.openai.com/api/docs/guides/realtime#beta-to-ga-migration) for the current GA interface and related Realtime docs.

320 

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

322| ------------- | ------------------------ | ----------------------- |

323| 2026‑05‑12 | OpenAI-Beta: realtime=v1 | Realtime API |

324 

325### 2025-09-15: `gpt-4o-realtime-preview` models

326 

327In September, 2025, we notified developers using `gpt-4o-realtime-preview` models of their deprecation and removal from the API in six months.

328 

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

330| ------------- | ------------------------------------ | ----------------------- |

331| 2026-05-07 | `gpt-4o-realtime-preview` | `gpt-realtime-1.5` |

332| 2026-05-07 | `gpt-4o-realtime-preview-2025-06-03` | `gpt-realtime-1.5` |

333| 2026-05-07 | `gpt-4o-realtime-preview-2024-12-17` | `gpt-realtime-1.5` |

334| 2026-05-07 | `gpt-4o-mini-realtime-preview` | `gpt-realtime-mini` |

335| 2026-05-07 | `gpt-4o-audio-preview` | `gpt-audio-1.5` |

336| 2026-05-07 | `gpt-4o-mini-audio-preview` | `gpt-audio-mini` |

337 

338### 2025-08-20: Assistants API

339 

340On August 26th, 2025, we notified developers using the Assistants API of its deprecation and removal from the API one year later, on August 26, 2026.

341 

342When we released the [Responses API](https://developers.openai.com/api/reference/resources/responses/methods/create) in [March 2025](https://developers.openai.com/api/docs/changelog), we announced plans to bring all Assistants API features to the easier to use Responses API, with a sunset date in 2026.

343 

344See the Assistants to Conversations [migration guide](https://developers.openai.com/api/docs/assistants/migration) to learn more about how to migrate your current integration to the Responses API and Conversations API.

345 

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

347| ------------- | -------------- | ----------------------------------- |

348| 2026‑08‑26 | Assistants API | Responses API and Conversations API |

349 

350### 2025-06-10: `gpt-4o-realtime-preview-2024-10-01`

351 

352On June 10th, 2025, we notified developers using `gpt-4o-realtime-preview-2024-10-01` of its deprecation and removal from the API in three months.

353 

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

355| ------------- | ------------------------------------ | ----------------------- |

356| 2025-10-10 | `gpt-4o-realtime-preview-2024-10-01` | `gpt-realtime-1.5` |

357 

358### 2025-06-10: `gpt-4o-audio-preview-2024-10-01`

359 

360On June 10th, 2025, we notified developers using `gpt-4o-audio-preview-2024-10-01` of its deprecation and removal from the API in three months.

361 

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

363| ------------- | --------------------------------- | ----------------------- |

364| 2025-10-10 | `gpt-4o-audio-preview-2024-10-01` | `gpt-audio-1.5` |

365 

366### 2025-04-28: `text-moderation`

367 

368On April 28th, 2025, we notified developers using `text-moderation` of its deprecation and removal from the API in six months.

369 

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

371| ------------- | ------------------------ | ----------------------- |

372| 2025-10-27 | `text-moderation-007` | `omni-moderation` |

373| 2025-10-27 | `text-moderation-stable` | `omni-moderation` |

374| 2025-10-27 | `text-moderation-latest` | `omni-moderation` |

375 

376### 2025-04-28: `o1-preview` and `o1-mini`

377 

378On April 28th, 2025, we notified developers using `o1-preview` and `o1-mini` of their deprecations and removal from the API in three months and six months respectively.

379 

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

381| ------------- | -------------- | ----------------------- |

382| 2025-07-28 | `o1-preview` | `o3` |

383| 2025-10-27 | `o1-mini` | `o4-mini` |

384 

385### 2025-04-14: GPT-4.5-preview

386 

387On April 14th, 2025, we notified developers that the `gpt-4.5-preview` model is deprecated and will be removed from the API in the coming months.

388 

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

390| ------------- | ----------------- | ----------------------- |

391| 2025-07-14 | `gpt-4.5-preview` | `gpt-4.1` |

392 

393### 2024-10-02: Assistants API beta v1

394 

395In [April 2024](https://developers.openai.com/api/docs/assistants/migration) when we released the v2 beta version of the Assistants API, we announced that access to the v1 beta would be shut off by the end of 2024. Access to the v1 beta will be discontinued on December 18, 2024.

396 

397See the Assistants API v2 beta [migration guide](https://developers.openai.com/api/docs/assistants/migration) to learn more about how to migrate your tool usage to the latest version of the Assistants API.

398 

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

400| ------------- | -------------------------- | -------------------------- |

401| 2024-12-18 | OpenAI-Beta: assistants=v1 | OpenAI-Beta: assistants=v2 |

402 

403### 2024-08-29: Fine-tuning training on babbage-002 and davinci-002 models

404 

405On August 29th, 2024, we notified developers fine-tuning `babbage-002` and `davinci-002` that new fine-tuning training runs on these models will no longer be supported starting October 28, 2024.

406 

407Fine-tuned models created from these base models are not affected by this deprecation, but you will no longer be able to create new fine-tuned versions with these models.

408 

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

410| ------------- | ----------------------------------------- | ----------------------- |

411| 2024-10-28 | New fine-tuning training on `babbage-002` | `gpt-4o-mini` |

412| 2024-10-28 | New fine-tuning training on `davinci-002` | `gpt-4o-mini` |

413 

414### 2024-06-06: GPT-4-32K and Vision Preview models

415 

416On June 6th, 2024, we notified developers using `gpt-4-32k` and `gpt-4-vision-preview` of their upcoming deprecations in one year and six months respectively. As of June 17, 2024, only existing users of these models will be able to continue using them.

417 

418| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |

419| ------------- | --------------------------- | -------------------------------------------------- | ----------------------- |

420| 2025-06-06 | `gpt-4-32k` | $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` |

421| 2025-06-06 | `gpt-4-32k-0613` | $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` |

422| 2025-06-06 | `gpt-4-32k-0314` | $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` |

423| 2024-12-06 | `gpt-4-vision-preview` | $10.00 / 1M input tokens + $30 / 1M output tokens | `gpt-4o` |

424| 2024-12-06 | `gpt-4-1106-vision-preview` | $10.00 / 1M input tokens + $30 / 1M output tokens | `gpt-4o` |

425 

426### 2023-11-06: Chat model updates

427 

428On November 6th, 2023, we [announced](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) the release of an updated GPT-3.5 Turbo model (which now comes by default with 16k context) along with deprecation of `gpt-3.5-turbo-0613` and ` gpt-3.5-turbo-16k-0613`. As of June 17, 2024, only existing users of these models will be able to continue using them.

429 

430| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |

431| ------------- | ------------------------ | -------------------------------------------------- | ----------------------- |

432| 2024-09-13 | `gpt-3.5-turbo-0613` | $1.50 / 1M input tokens + $2.00 / 1M output tokens | `gpt-3.5-turbo` |

433| 2024-09-13 | `gpt-3.5-turbo-16k-0613` | $3.00 / 1M input tokens + $4.00 / 1M output tokens | `gpt-3.5-turbo` |

434 

435Fine-tuned models created from these base models are not affected by this deprecation, but you will no longer be able to create new fine-tuned versions with these models.

436 

437### 2023-08-22: Fine-tunes endpoint

438 

439On August 22nd, 2023, we [announced](https://openai.com/blog/gpt-3-5-turbo-fine-tuning-and-api-updates) the new fine-tuning API (`/v1/fine_tuning/jobs`) and that the original `/v1/fine-tunes` API along with legacy models (including those fine-tuned with the `/v1/fine-tunes` API) will be shut down on January 04, 2024. This means that models fine-tuned using the `/v1/fine-tunes` API will no longer be accessible and you would have to fine-tune new models with the updated endpoint and associated base models.

440 

441#### Fine-tunes endpoint

442 

443| Shutdown date | System | Recommended replacement |

444| ------------- | ---------------- | ----------------------- |

445| 2024-01-04 | `/v1/fine-tunes` | `/v1/fine_tuning/jobs` |

446 

447### 2023-07-06: GPT and embeddings

448 126 

449On July 06, 2023, we [announced](https://openai.com/blog/gpt-4-api-general-availability) the upcoming retirements of older GPT-3 and GPT-3.5 models served via the completions endpoint. We also announced the upcoming retirement of our first-generation text embedding models. They will be shut down on January 04, 2024.

450 127 

451#### InstructGPT models

452 128 

453| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |

454| ------------- | ------------------ | ---------------------- | ------------------------ |

455| 2024-01-04 | `text-ada-001` | $0.40 / 1M tokens | `gpt-3.5-turbo-instruct` |

456| 2024-01-04 | `text-babbage-001` | $0.50 / 1M tokens | `gpt-3.5-turbo-instruct` |

457| 2024-01-04 | `text-curie-001` | $2.00 / 1M tokens | `gpt-3.5-turbo-instruct` |

458| 2024-01-04 | `text-davinci-001` | $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` |

459| 2024-01-04 | `text-davinci-002` | $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` |

460| 2024-01-04 | `text-davinci-003` | $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` |

461 129 

462Pricing for the replacement `gpt-3.5-turbo-instruct` model can be found on the [pricing page](https://openai.com/api/pricing).

463 130 

464#### Base GPT models

465 131 

466| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |132| Shutdown date | Affected model or feature | Listed replacement | Notice date |

467| ------------- | ------------------ | ---------------------- | ------------------------ |133| -------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- | ------------ |

468| 2024-01-04 | `ada` | $0.40 / 1M tokens | `babbage-002` |134| **Oct 23, 2026** | `gpt-3.5-turbo-0125`, `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.6-terra` | Apr 22, 2026 |

469| 2024-01-04 | `babbage` | $0.50 / 1M tokens | `babbage-002` |135| **Oct 23, 2026** | `gpt-4-0613`, `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.6-sol` | Apr 22, 2026 |

470| 2024-01-04 | `curie` | $2.00 / 1M tokens | `davinci-002` |136| **Oct 23, 2026** | `gpt-4-1106-preview` | `gpt-5.6-sol` | Apr 22, 2026 |

471| 2024-01-04 | `davinci` | $20.00 / 1M tokens | `davinci-002` |137| **Oct 23, 2026** | `gpt-4-turbo`, `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.6-sol` | Apr 22, 2026 |

472| 2024-01-04 | `code-davinci-002` | --- | `gpt-3.5-turbo-instruct` |138| **Oct 23, 2026** | `gpt-4.1-nano`, `gpt-4.1-nano-2025-04-14` | `gpt-5.6-luna` | Apr 22, 2026 |

473 139| **Oct 23, 2026** | `gpt-4o-2024-05-13` | `gpt-5.6-sol` | Apr 22, 2026 |

474Pricing for the replacement `babbage-002` and `davinci-002` models can be found on the [pricing page](https://openai.com/api/pricing).140| **Oct 23, 2026** | `gpt-image-1` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` | Apr 22, 2026 |

475 141| **Oct 23, 2026** | `o1-2024-12-17`, `o1` | `gpt-5.6-sol` | Apr 22, 2026 |

476#### Edit models & endpoint142| **Oct 23, 2026** | `o1-pro-2025-03-19`, `o1-pro` | `gpt-5.6-sol` (`reasoning.mode: pro`) | Apr 22, 2026 |

477 143| **Oct 23, 2026** | `o3-mini-2025-01-31`, `o3-mini` | `gpt-5.6-sol` | Apr 22, 2026 |

478| Shutdown date | Model / system | Recommended replacement |144| **Oct 23, 2026** | `ft-o4-mini-2025-04-16` | `gpt-5.6-terra` | Apr 22, 2026 |

479| ------------- | ----------------------- | ----------------------- |145| **Oct 23, 2026** | `o4-mini-2025-04-16`, `o4-mini` | `gpt-5.6-terra` | Apr 22, 2026 |

480| 2024-01-04 | `text-davinci-edit-001` | `gpt-4o` |146| **Oct 1, 2026** | `gpt-5.4-cyber` | The most capable cyber model available to you. | Sep 11, 2026 |

481| 2024-01-04 | `code-davinci-edit-001` | `gpt-4o` |147| **Sep 28, 2026** | `gpt-3.5-turbo-instruct` | `gpt-5.6-terra` | Sep 26, 2025 |

482| 2024-01-04 | `/v1/edits` | `/v1/chat/completions` |148| **Sep 28, 2026** | `babbage-002` | `gpt-5.6-terra` | Sep 26, 2025 |

483 149| **Sep 28, 2026** | `davinci-002` | `gpt-5.6-terra` | Sep 26, 2025 |

484#### Fine-tuning GPT models150| **Sep 28, 2026** | `gpt-3.5-turbo-1106` | `gpt-5.6-terra` | Sep 26, 2025 |

485 151| **Sep 24, 2026** | Videos API | No one-to-one replacement | Mar 24, 2026 |

486| Shutdown date | Deprecated model | Training price | Usage price | Recommended replacement |152| **Sep 24, 2026** | `sora-2` | No one-to-one replacement | Mar 24, 2026 |

487| ------------- | ---------------- | ------------------ | ------------------- | ---------------------------------------- |153| **Sep 24, 2026** | `sora-2-pro` | No one-to-one replacement | Mar 24, 2026 |

488| 2024-01-04 | `ada` | $0.40 / 1M tokens | $1.60 / 1M tokens | `babbage-002` |154| **Sep 24, 2026** | `sora-2-2025-10-06` | No one-to-one replacement | Mar 24, 2026 |

489| 2024-01-04 | `babbage` | $0.60 / 1M tokens | $2.40 / 1M tokens | `babbage-002` |155| **Sep 24, 2026** | `sora-2-2025-12-08` | No one-to-one replacement | Mar 24, 2026 |

490| 2024-01-04 | `curie` | $3.00 / 1M tokens | $12.00 / 1M tokens | `davinci-002` |156| **Sep 24, 2026** | `sora-2-pro-2025-10-06` | No one-to-one replacement | Mar 24, 2026 |

491| 2024-01-04 | `davinci` | $30.00 / 1M tokens | $120.00 / 1K tokens | `davinci-002`, `gpt-3.5-turbo`, `gpt-4o` |157| **Aug 26, 2026** | Assistants API | Responses API and Conversations API ([migration guide](https://developers.openai.com/api/docs/assistants/migration)) | Aug 26, 2025 |

492 158| **Aug 10, 2026** | `gpt-5.2-chat-latest` | `gpt-5.6-sol` | May 8, 2026 |

493#### First-generation text embedding models159| **Aug 10, 2026** | `gpt-5.3-chat-latest` | `gpt-5.6-sol` | May 8, 2026 |

494 160| **Jul 23, 2026** | `computer-use-preview-2025-03-11`, `computer-use-preview` | `gpt-5.6-terra` | Apr 22, 2026 |

495| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |161| **Jul 23, 2026** | `gpt-4o-mini-search-preview-2025-03-11` | `gpt-5.6-terra` | Apr 22, 2026 |

496| ------------- | ------------------------------- | ---------------------- | ------------------------ |162| **Jul 23, 2026** | `gpt-4o-search-preview-2025-03-11` | `gpt-5.6-terra` | Apr 22, 2026 |

497| 2024-01-04 | `text-similarity-ada-001` | $4.00 / 1M tokens | `text-embedding-3-small` |163| **Jul 23, 2026** | `gpt-5-chat-latest` | `gpt-5.6-sol` | Apr 22, 2026 |

498| 2024-01-04 | `text-search-ada-doc-001` | $4.00 / 1M tokens | `text-embedding-3-small` |164| **Jul 23, 2026** | `gpt-5-codex` | `gpt-5.6-sol` | Apr 22, 2026 |

499| 2024-01-04 | `text-search-ada-query-001` | $4.00 / 1M tokens | `text-embedding-3-small` |165| **Jul 23, 2026** | `gpt-5.1-chat-latest` | `gpt-5.6-sol` | Apr 22, 2026 |

500| 2024-01-04 | `code-search-ada-code-001` | $4.00 / 1M tokens | `text-embedding-3-small` |166| **Jul 23, 2026** | `gpt-5.1-codex` | `gpt-5.6-sol` | Apr 22, 2026 |

501| 2024-01-04 | `code-search-ada-text-001` | $4.00 / 1M tokens | `text-embedding-3-small` |167| **Jul 23, 2026** | `gpt-5.1-codex-max` | `gpt-5.6-sol` | Apr 22, 2026 |

502| 2024-01-04 | `text-similarity-babbage-001` | $5.00 / 1M tokens | `text-embedding-3-small` |168| **Jul 23, 2026** | `gpt-5.1-codex-mini` | `gpt-5.6-terra` | Apr 22, 2026 |

503| 2024-01-04 | `text-search-babbage-doc-001` | $5.00 / 1M tokens | `text-embedding-3-small` |169| **Jul 23, 2026** | `gpt-audio-mini-2025-10-06` | `gpt-audio-1.5` | Apr 22, 2026 |

504| 2024-01-04 | `text-search-babbage-query-001` | $5.00 / 1M tokens | `text-embedding-3-small` |170| **Jul 23, 2026** | `gpt-realtime-mini-2025-10-06` | `gpt-realtime-2.1-mini` | Apr 22, 2026 |

505| 2024-01-04 | `code-search-babbage-code-001` | $5.00 / 1M tokens | `text-embedding-3-small` |171| **Jul 23, 2026** | `o3-deep-research-2025-06-26`, `o3-deep-research` | `gpt-5.6-sol` | Apr 22, 2026 |

506| 2024-01-04 | `code-search-babbage-text-001` | $5.00 / 1M tokens | `text-embedding-3-small` |172| **Jul 23, 2026** | `o4-mini-deep-research-2025-06-26`, `o4-mini-deep-research` | `gpt-5.6-sol` | Apr 22, 2026 |

507| 2024-01-04 | `text-similarity-curie-001` | $20.00 / 1M tokens | `text-embedding-3-small` |173| **Jul 23, 2026** | `gpt-5.2-codex` | `gpt-5.6-sol` | Apr 22, 2026 |

508| 2024-01-04 | `text-search-curie-doc-001` | $20.00 / 1M tokens | `text-embedding-3-small` |174| **May 12, 2026** | `dall-e-2` | `gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini` | Nov 14, 2025 |

509| 2024-01-04 | `text-search-curie-query-001` | $20.00 / 1M tokens | `text-embedding-3-small` |175| **May 12, 2026** | `dall-e-3` | `gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini` | Nov 14, 2025 |

510| 2024-01-04 | `text-similarity-davinci-001` | $200.00 / 1M tokens | `text-embedding-3-small` |176| **May 12, 2026** | OpenAI-Beta: realtime=v1 | [Realtime API migration guide](https://developers.openai.com/api/docs/guides/realtime#beta-to-ga-migration) | Sep 15, 2025 |

511| 2024-01-04 | `text-search-davinci-doc-001` | $200.00 / 1M tokens | `text-embedding-3-small` |177| **May 7, 2026** | `gpt-4o-realtime-preview` | `gpt-realtime-1.5` | Sep 15, 2025 |

512| 2024-01-04 | `text-search-davinci-query-001` | $200.00 / 1M tokens | `text-embedding-3-small` |178| **May 7, 2026** | `gpt-4o-realtime-preview-2025-06-03` | `gpt-realtime-1.5` | Sep 15, 2025 |

513 179| **May 7, 2026** | `gpt-4o-realtime-preview-2024-12-17` | `gpt-realtime-1.5` | Sep 15, 2025 |

514### 2023-06-13: Updated chat models180| **May 7, 2026** | `gpt-4o-mini-realtime-preview` | `gpt-realtime-mini` | Sep 15, 2025 |

515 181| **May 7, 2026** | `gpt-4o-audio-preview` | `gpt-audio-1.5` | Sep 15, 2025 |

516On June 13, 2023, we announced new chat model versions in the [Function calling and other API updates](https://openai.com/blog/function-calling-and-other-api-updates) blog post. The three original versions will be retired in June 2024 at the earliest. As of January 10, 2024, only existing users of these models will be able to continue using them.182| **May 7, 2026** | `gpt-4o-mini-audio-preview` | `gpt-audio-mini` | Sep 15, 2025 |

517 183| **Mar 26, 2026** | `gpt-4-0314` | `gpt-5`, or `gpt-4.1` for latency-sensitive tasks that don't require reasoning | Sep 26, 2025 |

518| Shutdown date | Legacy model | Legacy model price | Recommended replacement |184| **Mar 26, 2026** | `gpt-4-0125-preview` (including `gpt-4-turbo-preview` and `gpt-4-turbo-preview-completions`, which point to this snapshot) | `gpt-5`, or `gpt-4.1` for latency-sensitive tasks that don't require reasoning | Sep 26, 2025 |

519| ---------------------- | ------------ | ---------------------------------------------------- | ----------------------- |185| **Feb 17, 2026** | `chatgpt-4o-latest` | `gpt-5.1-chat-latest` | Nov 18, 2025 |

520| at earliest 2024-06-13 | `gpt-4-0314` | $30.00 / 1M input tokens + $60.00 / 1M output tokens | `gpt-4o` |186| **Feb 12, 2026** | `codex-mini-latest` | `gpt-5-codex-mini` | Nov 17, 2025 |

521 187| **Oct 27, 2025** | `text-moderation-007` | `omni-moderation` | Apr 28, 2025 |

522| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |188| **Oct 27, 2025** | `text-moderation-stable` | `omni-moderation` | Apr 28, 2025 |

523| ------------- | -------------------- | ----------------------------------------------------- | ----------------------- |189| **Oct 27, 2025** | `text-moderation-latest` | `omni-moderation` | Apr 28, 2025 |

524| 2024-09-13 | `gpt-3.5-turbo-0301` | $15.00 / 1M input tokens + $20.00 / 1M output tokens | `gpt-3.5-turbo` |190| **Oct 27, 2025** | `o1-mini` | `o4-mini` | Apr 28, 2025 |

525| 2025-06-06 | `gpt-4-32k-0314` | $60.00 / 1M input tokens + $120.00 / 1M output tokens | `gpt-4o` |191| **Oct 10, 2025** | `gpt-4o-realtime-preview-2024-10-01` | `gpt-realtime-1.5` | Jun 10, 2025 |

526 192| **Oct 10, 2025** | `gpt-4o-audio-preview-2024-10-01` | `gpt-audio-1.5` | Jun 10, 2025 |

527### 2023-03-20: Codex models193| **Jul 28, 2025** | `o1-preview` | `o3` | Apr 28, 2025 |

528 194| **Jul 14, 2025** | `gpt-4.5-preview` | `gpt-4.1` | Apr 14, 2025 |

529| Shutdown date | Deprecated model | Recommended replacement |195| **Jun 6, 2025** | `gpt-4-32k` Historical price $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` | Jun 6, 2024 |

530| ------------- | ------------------ | ----------------------- |196| **Jun 6, 2025** | `gpt-4-32k-0613` Historical price $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` | Jun 6, 2024 |

531| 2023-03-23 | `code-davinci-002` | `gpt-4o` |197| **Jun 6, 2025** | `gpt-4-32k-0314` Historical price $60.00 / 1M input tokens + $120 / 1M output tokens | `gpt-4o` | Jun 13, 2023 |

532| 2023-03-23 | `code-davinci-001` | `gpt-4o` |198| **Dec 18, 2024** | OpenAI-Beta: assistants=v1 | OpenAI-Beta: assistants=v2 ([migration guide](https://developers.openai.com/api/docs/assistants/migration)) | Oct 2, 2024 |

533| 2023-03-23 | `code-cushman-002` | `gpt-4o` |199| **Dec 6, 2024** | `gpt-4-vision-preview` Historical price $10.00 / 1M input tokens + $30 / 1M output tokens | `gpt-4o` | Jun 6, 2024 |

534| 2023-03-23 | `code-cushman-001` | `gpt-4o` |200| **Dec 6, 2024** | `gpt-4-1106-vision-preview` Historical price $10.00 / 1M input tokens + $30 / 1M output tokens | `gpt-4o` | Jun 6, 2024 |

535 201| **Oct 28, 2024** | New fine-tuning training on `babbage-002` | `gpt-4o-mini` | Aug 29, 2024 |

536### 2022-06-03: Legacy endpoints202| **Oct 28, 2024** | New fine-tuning training on `davinci-002` | `gpt-4o-mini` | Aug 29, 2024 |

537 203| **Sep 13, 2024** | `gpt-3.5-turbo-0613` Historical price $1.50 / 1M input tokens + $2.00 / 1M output tokens | `gpt-3.5-turbo` | Nov 6, 2023 |

538| Shutdown date | System | Recommended replacement |204| **Sep 13, 2024** | `gpt-3.5-turbo-16k-0613` Historical price $3.00 / 1M input tokens + $4.00 / 1M output tokens | `gpt-3.5-turbo` | Nov 6, 2023 |

539| ------------- | --------------------- | ----------------------------------------------------------------------------------------------------- |205| **Sep 13, 2024** | `gpt-3.5-turbo-0301` Historical price $15.00 / 1M input tokens + $20.00 / 1M output tokens | `gpt-3.5-turbo` | Jun 13, 2023 |

540| 2022-12-03 | `/v1/engines` | [/v1/models](https://platform.openai.com/docs/api-reference/models/list) |206| **Jun 13, 2024** Earliest estimate | `gpt-4-0314` Historical price $30.00 / 1M input tokens + $60.00 / 1M output tokens | `gpt-4o` | Jun 13, 2023 |

541| 2022-12-03 | `/v1/search` | [View transition guide](https://help.openai.com/en/articles/6272952-search-transition-guide) |207| **Jan 4, 2024** | `/v1/fine-tunes` | `/v1/fine_tuning/jobs` | Aug 22, 2023 |

542| 2022-12-03 | `/v1/classifications` | [View transition guide](https://help.openai.com/en/articles/6272941-classifications-transition-guide) |208| **Jan 4, 2024** | `text-ada-001` Historical price $0.40 / 1M tokens | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

543| 2022-12-03 | `/v1/answers` | [View transition guide](https://help.openai.com/en/articles/6233728-answers-transition-guide) |209| **Jan 4, 2024** | `text-babbage-001` Historical price $0.50 / 1M tokens | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

544 210| **Jan 4, 2024** | `text-curie-001` Historical price $2.00 / 1M tokens | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

545### Plain-text aliases211| **Jan 4, 2024** | `text-davinci-001` Historical price $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

546 212| **Jan 4, 2024** | `text-davinci-002` Historical price $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

547- gpt-image-2 | gpt-image-2-2026-04-21213| **Jan 4, 2024** | `text-davinci-003` Historical price $20.00 / 1M tokens | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

548- gpt-5.4-nano | gpt-5.4-nano-2026-03-17214| **Jan 4, 2024** | `ada` Historical price $0.40 / 1M tokens | `babbage-002` | Jul 6, 2023 |

549- gpt-5.1 | gpt-5.1-2025-11-13215| **Jan 4, 2024** | `babbage` Historical price $0.50 / 1M tokens | `babbage-002` | Jul 6, 2023 |

550- gpt-4o-mini-tts | gpt-4o-mini-tts-2025-03-20216| **Jan 4, 2024** | `curie` Historical price $2.00 / 1M tokens | `davinci-002` | Jul 6, 2023 |

551- gpt-4o-mini-tts | gpt-4o-mini-tts-2025-12-15217| **Jan 4, 2024** | `davinci` Historical price $20.00 / 1M tokens | `davinci-002` | Jul 6, 2023 |

552- gpt-4o-mini-transcribe | gpt-4o-mini-transcribe-2025-12-15218| **Jan 4, 2024** | `code-davinci-002` (base GPT models) | `gpt-3.5-turbo-instruct` | Jul 6, 2023 |

553- gpt-realtime | gpt-realtime-2025-08-28219| **Jan 4, 2024** | `text-davinci-edit-001` | `gpt-4o` | Jul 6, 2023 |

554- gpt-audio | gpt-audio-2025-08-28220| **Jan 4, 2024** | `code-davinci-edit-001` | `gpt-4o` | Jul 6, 2023 |

555- gpt-realtime-mini | gpt-realtime-mini-2025-12-15221| **Jan 4, 2024** | `/v1/edits` | `/v1/chat/completions` | Jul 6, 2023 |

556- gpt-audio-mini | gpt-audio-mini-2025-12-15222| **Jan 4, 2024** | Fine-tuning on `ada` Training price $0.40 / 1M tokens. Usage price $1.60 / 1M tokens | `babbage-002` | Jul 6, 2023 |

557- gpt-5 | gpt-5-2025-08-07223| **Jan 4, 2024** | Fine-tuning on `babbage` Training price $0.60 / 1M tokens. Usage price $2.40 / 1M tokens | `babbage-002` | Jul 6, 2023 |

558- gpt-5-mini | gpt-5-mini-2025-08-07224| **Jan 4, 2024** | Fine-tuning on `curie` Training price $3.00 / 1M tokens. Usage price $12.00 / 1M tokens | `davinci-002` | Jul 6, 2023 |

559- gpt-5-nano | gpt-5-nano-2025-08-07225| **Jan 4, 2024** | Fine-tuning on `davinci` Training price $30.00 / 1M tokens. Usage price $120.00 / 1K tokens | `davinci-002`, `gpt-3.5-turbo`, `gpt-4o` | Jul 6, 2023 |

560- gpt-5-pro | gpt-5-pro-2025-10-06226| **Jan 4, 2024** | `text-similarity-ada-001` Historical price $4.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

561- o3 | o3-2025-04-16227| **Jan 4, 2024** | `text-search-ada-doc-001` Historical price $4.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

562- o3-pro | o3-pro-2025-06-10228| **Jan 4, 2024** | `text-search-ada-query-001` Historical price $4.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

563- gpt-image-1.5 | gpt-image-1.5-2025-12-16229| **Jan 4, 2024** | `code-search-ada-code-001` Historical price $4.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

564- gpt-3.5-turbo-0125 | gpt-3.5-turbo, gpt-3.5-turbo-completions230| **Jan 4, 2024** | `code-search-ada-text-001` Historical price $4.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

565- gpt-4-0613 | gpt-4, gpt-4-0613-completions, gpt-4-completions231| **Jan 4, 2024** | `text-similarity-babbage-001` Historical price $5.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

566- gpt-4-turbo | gpt-4-turbo-2024-04-09, gpt-4-turbo-completions232| **Jan 4, 2024** | `text-search-babbage-doc-001` Historical price $5.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

567- gpt-4.1-nano | gpt-4.1-nano-2025-04-14233| **Jan 4, 2024** | `text-search-babbage-query-001` Historical price $5.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

568- o1-2024-12-17 | o1234| **Jan 4, 2024** | `code-search-babbage-code-001` Historical price $5.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

569- o1-pro-2025-03-19 | o1-pro235| **Jan 4, 2024** | `code-search-babbage-text-001` Historical price $5.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

570- o3-mini-2025-01-31 | o3-mini236| **Jan 4, 2024** | `text-similarity-curie-001` Historical price $20.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

571- o4-mini-2025-04-16 | o4-mini237| **Jan 4, 2024** | `text-search-curie-doc-001` Historical price $20.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

572- computer-use-preview-2025-03-11 | computer-use-preview238| **Jan 4, 2024** | `text-search-curie-query-001` Historical price $20.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

573- o3-deep-research-2025-06-26 | o3-deep-research239| **Jan 4, 2024** | `text-similarity-davinci-001` Historical price $200.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

574- o4-mini-deep-research-2025-06-26 | o4-mini-deep-research240| **Jan 4, 2024** | `text-search-davinci-doc-001` Historical price $200.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

241| **Jan 4, 2024** | `text-search-davinci-query-001` Historical price $200.00 / 1M tokens | `text-embedding-3-small` | Jul 6, 2023 |

242| **Mar 23, 2023** | `code-davinci-002` (Codex models) | `gpt-4o` | Mar 20, 2023 |

243| **Mar 23, 2023** | `code-davinci-001` | `gpt-4o` | Mar 20, 2023 |

244| **Mar 23, 2023** | `code-cushman-002` | `gpt-4o` | Mar 20, 2023 |

245| **Mar 23, 2023** | `code-cushman-001` | `gpt-4o` | Mar 20, 2023 |

246| **Dec 3, 2022** | `/v1/engines` | [/v1/models](https://platform.openai.com/docs/api-reference/models/list) | Jun 3, 2022 |

247| **Dec 3, 2022** | `/v1/search` | [View transition guide](https://help.openai.com/en/articles/6272952-search-transition-guide) | Jun 3, 2022 |

248| **Dec 3, 2022** | `/v1/classifications` | [View transition guide](https://help.openai.com/en/articles/6272941-classifications-transition-guide) | Jun 3, 2022 |

249| **Dec 3, 2022** | `/v1/answers` | [View transition guide](https://help.openai.com/en/articles/6233728-answers-transition-guide) | Jun 3, 2022 |

250 

251 

252 

253 

254### Historical notes

255 

256- Fine-tuned versions of the [legacy GPT models shut down in October 2026](https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots) followed the same shutdown schedule as their underlying base models.

257- The [`codex-mini-latest` shutdown](https://developers.openai.com/api/docs/deprecations#2025-11-17-codex-mini-latest-model-snapshot) also ended support for the legacy local shell tool. For new integrations, use the [shell tool](https://developers.openai.com/api/docs/guides/tools-shell).

258- The [Assistants API notice](https://developers.openai.com/api/docs/deprecations#2025-08-20-assistants-api) followed the release of the Responses API in [March 2025](https://developers.openai.com/api/docs/changelog). We first announced plans to retire the Assistants API v1 beta when we [released v2 in April 2024](https://developers.openai.com/api/docs/assistants/migration).

259- The October 2024 shutdown for [fine-tuning training on `babbage-002` and `davinci-002`](https://developers.openai.com/api/docs/deprecations#2024-08-29-fine-tuning-training-on-babbage-002-and-davinci-002-models) applied to creating new fine-tuned models. Existing fine-tuned models were unaffected by that change.

260- The June 6, 2024 notice reconfirmed the retirement of `gpt-4-32k-0314`. Starting June 17, 2024, access to the GPT-4-32K and Vision Preview models and the GPT-3.5 Turbo snapshots announced in [November 2023](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) was limited to existing users. Existing fine-tuned models from those GPT-3.5 Turbo snapshots were unaffected by that shutdown.

261- The [legacy fine-tunes endpoint shutdown](https://developers.openai.com/api/docs/deprecations#2023-08-22-fine-tunes-endpoint) also removed access to models trained with that endpoint. Developers had to train new models through the [updated fine-tuning API](https://openai.com/blog/gpt-3-5-turbo-fine-tuning-and-api-updates).

262- The [July 2023 announcement](https://openai.com/blog/gpt-4-api-general-availability) covered older GPT-3 and GPT-3.5 models served through the completions endpoint and first-generation text embedding models. See the [pricing page](https://openai.com/api/pricing) for current model pricing.

263- The [June 2023 announcement](https://openai.com/blog/function-calling-and-other-api-updates) gave an earliest retirement date of June 13, 2024 for the original chat models. Starting January 10, 2024, access was limited to existing users. See the [March 2026 shutdown notice](https://developers.openai.com/api/docs/deprecations#2025-09-26-legacy-gpt-model-snapshots-march-2026-shutdown) for the final shutdown date of `gpt-4-0314`.