Model Comparison
Compare two models side by side to make informed decisions based on pricing, specifications, and performance.
gpt-audio
OpenAI
multimodalJSON output not supported
The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.
Pricing
Input
$2.75/M
Output
$11.00/M
Cached Input
—
Specifications
Context
128,000
Maximum Output
16,384
Inputtext, audio
Outputtext, audio
No model selected