GPT Audio

OpenAI

The GPT Audio model is OpenAI's first generally available audio model. It features an upgraded decoder for more natural sounding voices and maintains better voice consistency.

Try Now

Technical Specifications

Context Window

128,000 tokens

Max Output

16,384 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$2.50

Non-Reasoning Output

$10

Retired

Made legacy on

Reason

Audio model; not applicable for text chat

Recommended Replacement

GPT-5.5

Retired on