GPT-Audio Mini
GPT-Audio Mini is a deprecated lower-cost audio model for Chat Completions. It accepts and returns text or audio through a REST-style request flow.
Deprecated API; check access details
The Mini audio route is not Realtime Mini
Its documented window is 128,000 tokens with a 16,384-token output ceiling. The December 2025 snapshot belongs to the Chat Completions audio family. Realtime Mini uses a different endpoint and session contract.GPT-Audio Mini official model documentation
Review an existing integration
Practical guidance. For asynchronous voice messages, compare complete input and output recordings using the same task. Confirm that the replacement returns the audio and text fields the application expects. Avoid changing connection architecture as an unnoticed part of a model update.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Access | API |
| Model identifiers | gpt-audio-minigpt-audio-mini-2025-12-15 |
| Context window | 128,000 tokens Published context for this deprecated release GPT-Audio Mini official model documentation |
| Maximum output | 16,384 tokens Published maximum output, bounded by the remaining context GPT-Audio Mini official model documentation |
| Provider status | Deprecated in the current OpenAI model catalog; confirm remaining account access.GPT-Audio Mini official model documentation |
Related models
GPT-Audio is a deprecated audio model accessed through Chat Completions.
Launch date not confirmedDeprecated API; check access detailsAPI- GPT-Audio-1.5
OpenAI · GPT Audio
GPT-Audio-1.5 works with audio through Chat Completions.
Launch date not confirmedAPI