OhMyGPT

gpt-audio

Common Name: GPT Audio

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.

OpenAI

multimodal

Model Specifications

Context Window

128000

Maximum Input

Unknown

Maximum Output

16384

Input/Output Types

Input Type

📝text

🎵audio

Output Type

📝text

🎵audio

Pricing Information (USD)

+10%

Input Price

$2.75

/MTokens

Output Price

$11.00

/MTokens

Audio Input

$44.00

/MTokens

Audio Output

$88.00

/MTokens

Log in to access professional data analysis

Log in to view model usage statistics, consumption trend analysis, and efficiency evaluation, helping you better manage AI resources