AtlasAI Center AI tool intelligence
OpenAI · API model

GPT Audio

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

Context
128K
Input / 1M
$2.5
Output / 1M
$10
Released
Jan 19, 2026
Specifications

GPT Audio specs

Provider
OpenAI
Type
API model
Model ID
openai/gpt-audio
Context window
128,000 tokens128K
Input price
$2.5per 1M input tokens
Output price
$10per 1M output tokens
Accepts
audio, text
Produces
audio, text
Released
Jan 19, 2026
Source
OpenRouter
Overview

About GPT Audio

GPT Audio is an API model from OpenAI, released on Jan 19, 2026, with a context window of 128,000 tokens, pricing of $2.5 per million input tokens and $10 per million output tokens. It accepts audio, text input and produces audio, text output.

At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.035.

Specs are sourced from OpenRouter and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.

Tool callingStructured outputsJSON mode
FAQ

GPT Audio questions

What is the context window of GPT Audio?

GPT Audio supports a context window of 128,000 tokens.

How much does GPT Audio cost?

GPT Audio is listed at $2.5 per million input tokens and $10 per million output tokens on OpenRouter.

When was GPT Audio released?

GPT Audio was published on Jan 19, 2026.

What inputs does GPT Audio accept?

GPT Audio accepts audio, text input and produces audio, text output.