# gpt-audio-mini — AI model deprecation and retirement dates by provider

For gpt-audio-mini, provider is OpenAI; lifecycle status is Deprecated; deprecation announced is July 20, 2026; shutdown / retirement date is Jan 20, 2027; recommended replacement is gpt-audio-1.5, verified against its source on 2026-08-12.

- **Provider:** OpenAI _(verified: appears in the quote below)_
- **Model ID / API name:** gpt-audio-mini _(verified: appears in the quote below)_
- **Lifecycle status:** Deprecated _(verified: appears in the quote below)_
- **Deprecation announced:** July 20, 2026 _(verified: appears in the quote below)_
- **Shutdown / retirement date:** Jan 20, 2027 _(verified: appears in the quote below)_
- **Recommended replacement:** gpt-audio-1.5 _(verified: appears in the quote below)_
- **Human-readable model name:** gpt-audio-mini _(per learn.microsoft.com, not stated by the source above)_
- **Platform / deployment scope:** Azure / Microsoft Foundry _(per learn.microsoft.com, not stated by the source above)_

## What the source says

> You can expect that a legacy model or endpoint will be deprecated at some point in the future. Upcoming deprecations Upcoming deprecations are listed below, with the most recent announcements at the top. 2026-07-20: Legacy audio, realtime, and transcription models On 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. Shutdown date | Model family / snapshot | Recommended replacement | Jan 20, 2027 | gpt-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-realtime-mini | gpt-realtime-2.1-mini | Jan 20, 2027 | gpt-audio-mini | gpt-audio-1.5 |

## Sources disagree

More than one authority states this, and they do not state the same
thing. Both are reproduced with the source each came from.

### Provider

platform.openai.com says provider is **OpenAI**, as of 2026-08-12.

> You can expect that a legacy model or endpoint will be deprecated at some point in the future. Upcoming deprecations Upcoming deprecations are listed below, with the most recent announcements at the top. 2026-07-20: Legacy audio, realtime, and transcription models On 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. Shutdown date | Model family / snapshot | Recommended replacement | Jan 20, 2027 | gpt-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-realtime-mini | gpt-realtime-2.1-mini | Jan 20, 2027 | gpt-audio-mini | gpt-audio-1.5 |

Source: https://platform.openai.com/docs/deprecations

learn.microsoft.com says provider is **Microsoft Azure / Foundry**, as of 2026-08-12.

> GA | 2027-08-24 | — | gpt-audio-mini | 2025-10-06 | GA | 2027-04-06 |

Source: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule


### Lifecycle status

platform.openai.com says lifecycle status is **Deprecated**, as of 2026-08-12.

> You can expect that a legacy model or endpoint will be deprecated at some point in the future. Upcoming deprecations Upcoming deprecations are listed below, with the most recent announcements at the top. 2026-07-20: Legacy audio, realtime, and transcription models On 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. Shutdown date | Model family / snapshot | Recommended replacement | Jan 20, 2027 | gpt-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-realtime-mini | gpt-realtime-2.1-mini | Jan 20, 2027 | gpt-audio-mini | gpt-audio-1.5 |

Source: https://platform.openai.com/docs/deprecations

learn.microsoft.com says lifecycle status is **GA**, as of 2026-08-12.

> GA | 2027-08-24 | — | gpt-audio-mini | 2025-10-06 | GA | 2027-04-06 |

Source: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule


### Shutdown / retirement date

platform.openai.com says shutdown / retirement date is **Jan 20, 2027**, as of 2026-08-12.

> You can expect that a legacy model or endpoint will be deprecated at some point in the future. Upcoming deprecations Upcoming deprecations are listed below, with the most recent announcements at the top. 2026-07-20: Legacy audio, realtime, and transcription models On 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. Shutdown date | Model family / snapshot | Recommended replacement | Jan 20, 2027 | gpt-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-audio | gpt-audio-1.5 | Jan 20, 2027 | gpt-4o-realtime | gpt-realtime-2.1 | Jan 20, 2027 | gpt-realtime-mini | gpt-realtime-2.1-mini | Jan 20, 2027 | gpt-audio-mini | gpt-audio-1.5 |

Source: https://platform.openai.com/docs/deprecations

learn.microsoft.com says shutdown / retirement date is **2027-04-06**, as of 2026-08-12.

> GA | 2027-08-24 | — | gpt-audio-mini | 2025-10-06 | GA | 2027-04-06 |

Source: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule


## Source

- https://platform.openai.com/docs/deprecations
- https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule

Last verified: 2026-08-12. Review by: 2026-09-11.
Part of [AI model deprecation and retirement dates by provider](https://referencesource.org/ai-model-deprecation-and-retirement/).