GPT-4o Audio Deprecated
GPT-4o Audio is a model from OpenAI, listed under Voice and realtime. It was released on Oct 1, 2024.
This model is scheduled for retirement. Plan a migration.
- Headline price
- No data
- Context window
- 128k tokens
- Max output
- 16k
- Knowledge cutoff
- Oct 2023
Current prices
No public API price
This model is distributed as open weights. Running cost depends on your own hardware.
Price history
No price change recorded for this model yet.
Alternatives
Same category, closest price, other providers first.
More from OpenAI
| # | Model | Price | Released | Price change |
|---|---|---|---|---|
| 1 |
GPT-Live 1
OpenAI
|
$0.05 / minute | Sep 10, 2026 | |
| 2 |
GPT-Audio-1.5
OpenAI
|
$32.00 / 1M audio tokens | Feb 23, 2026 | |
| 3 |
GPT-Realtime-2.1
OpenAI
|
$32.00 / 1M audio tokens | Jul 6, 2026 | |
| 4 |
GPT-Realtime-2.1 Mini
OpenAI
|
$10.00 / 1M audio tokens | No data | |
| 5 |
GPT-Realtime-Translate
OpenAI
|
$0.034 / minute | May 7, 2026 |
Spotted something wrong? Report it
Frequently asked questions
What is the context window of GPT-4o Audio?
GPT-4o Audio accepts up to 128k tokens per request. It can write up to 16k tokens in one response.
Is GPT-4o Audio still available?
It still works, but it is deprecated: OpenAI plans to retire it.
When was GPT-4o Audio released?
GPT-4o Audio was released in Oct 1, 2024.
What is the API model ID for GPT-4o Audio?
Use gpt-4o-audio-preview when calling the OpenAI API.
What are the alternatives to GPT-4o Audio?
Models in the same category at a similar price include Gemini 3.5 Live Translate (Google), GPT-Audio-1.5 (OpenAI), Gemini 3.8 Live (Google) and GPT-Realtime-Translate (OpenAI).