Back to Models

gpt-4o-audio-preview

gpt-4o-audio-preview

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs...

Modalities

Input

audiotext

Output

audiotext
Pricing
Cost per 1 million tokens
Input
$3
Output
$12
Model Specs
Context Window
128,000
Max Output
16,384
Release Date
2025-08-15
Knowledge Cutoff
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2026-03-15

Provider: