GPT-4o Audio
GPT-4o models capable of audio inputs and outputs
Specs
- Context
- 128K
- Max output
- 16.4K
- Input price
- —
- Output price
- —
- Released
- —
Context
- Context window
- 128K
- Max input
- —
- Max output
- 16.4K
Pricing
- Not published
Modalities
- Input
- TextAudio
- Output
- TextAudio
API
- API types
Reasoning
- Not published
Info
- Status
- Retired
- Released
- —
- Knowledge cutoff
- 2023-10-01
Features
- Confirmed
How to call
1 provider
openaimodel = gpt-4o-audio-preview
chat
POSThttps://api.openai.com/v1/chat/completions
JSON
Standard format
{
"id": "gpt-4o-audio-preview",
"object": "model",
"created": null,
"owned_by": "openai",
"name": "GPT-4o Audio",
"api": {
"types": [
"chat"
]
},
"limits": {
"context": 128000,
"input": null,
"output": 16384
},
"modalities": {
"input": [
"text",
"audio"
],
"output": [
"text",
"audio"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [
"tools",
"streaming"
],
"info": {
"status": "retired",
"release_date": null,
"knowledge_cutoff": "2023-10-01",
"description": "GPT-4o models capable of audio inputs and outputs",
"docs": "https://developers.openai.com/api/docs/models/gpt-4o-audio-preview",
"verified_at": "2026-10-11"
}
}Official sources
2