# gpt-4o-mini-tts

Calls to the model gpt-4o-mini-tts on OpenAI stop working on January 6, 2027.

On January 6, 2027, OpenAI will shut down model gpt-4o-mini-tts. Any calls requesting model gpt-4o-mini-tts will fail after that date.

## The error OpenAI returns once gpt-4o-mini-tts is gone

HTTP 404

```json
{"error":{"message":"The model `gpt-4o-mini-tts` 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

Migrate to the recommended replacement gpt-realtime-2.1-mini. This transition requires more than updating the model identifier, as gpt-realtime-2.1-mini is not served on /v1/audio/speech and runs only on the Realtime API at /v1/realtime over WebRTC or WebSocket. Responses return as base64 audio chunks in response.output_audio.delta events rather than as an mp3 or wav response body.

gpt-realtime-2.1-mini is not served on /v1/audio/speech: it runs only on the Realtime API (/v1/realtime, over WebRTC or WebSocket). Audio comes back as base64 chunks in response.output_audio.delta events (for example audio/pcm at 24 kHz), not as an mp3 or wav response body.

- API: OpenAI (api.openai.com)
- Model: gpt-4o-mini-tts
- Kind: Model retirement
- Takes effect: January 6, 2027
- Calls after that day: fail
- Calls it hits: `model gpt-4o-mini-tts`
- 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-4o-mini-tts/

## OpenAI's words

> Shutdown date: Jan 6, 2027; Model / system: gpt-4o-mini-tts | gpt-4o-mini-tts-2025-03-20; Recommended replacement: gpt-realtime-2.1-mini

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