# gpt-audio-2025-08-28

Calls to the model gpt-audio-2025-08-28 on OpenAI stop working on January 20, 2027.

On January 20, 2027, the snapshot model gpt-audio-2025-08-28 will be retired. Requests specifying model gpt-audio-2025-08-28 will fail after this date. OpenAI has set this shutdown date for the snapshot within the gpt-audio family.

## The error OpenAI returns once gpt-audio-2025-08-28 is gone

HTTP 404

```json
{"error":{"message":"The model `gpt-audio-2025-08-28` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations","type":"invalid_request_error","param":null,"code":"model_not_found"}}
```

## What to use instead

Move to gpt-audio-1.5, which is recommended by OpenAI as the replacement.

- API: OpenAI (api.openai.com)
- Model: gpt-audio-2025-08-28
- Kind: Model retirement
- Takes effect: January 20, 2027
- Calls after that day: fail
- Calls it hits: `model gpt-audio-2025-08-28`
- Source: [Deprecations page](https://developers.openai.com/api/docs/deprecations)
- Verified: November 6, 2026, against OpenAI's own pages
- Page: https://www.okapi.bot/models/openai/gpt-audio-2025-08-28/

## OpenAI's words

> Shutdown date: Jan 20, 2027; Model family / snapshot: gpt-audio | gpt-audio-2025-08-28; Recommended replacement: gpt-audio-1.5

Okapi finds the calls this change hits in your repo and opens the pull request with the fix: https://github.com/apps/okapi-agent